Trajectory quality evaluation method, device and electronic device based on knowledge graph

Abstract

The present disclosure provides a trajectory quality evaluation method, device, and electronic device based on a knowledge graph, relating to the fields of autonomous driving and high-precision map technology. The method includes: in response to a trajectory query request, determining the target action trajectory corresponding to the trajectory query request; obtaining a knowledge graph pre-constructed based on historical action trajectories; based on the knowledge graph, determining the target attribute information of the target action trajectory, and using the target attribute information as the quality evaluation result of the target action trajectory. The technical solution disclosed in the present disclosure obtains the quality evaluation result of the target action trajectory through the knowledge graph, has low cost, and can meet dynamic query requirements; by performing quality evaluation on the action trajectory, the utilization rate of the action trajectory can be effectively improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to the field of autonomous driving and high-precision map technology. Background Art

[0002] With the advancement of computer and mobile communication technologies, mobile terminals are becoming increasingly powerful. More and more users are using electronic maps on their mobile devices for navigation. Electronic maps can access movement trajectories from a variety of data sources, including various applications, such as car rental and delivery apps. To better utilize movement trajectories, an effective evaluation method for their quality is needed. Summary of the Invention

[0003] The present disclosure provides a trajectory quality evaluation method, device, and electronic device based on a knowledge graph.

[0004] According to one aspect of the present disclosure, a method for evaluating trajectory quality based on a knowledge graph is provided, comprising:

[0005] In response to the trajectory query request, determining a target action trajectory corresponding to the trajectory query request;

[0006] Obtain a knowledge graph pre-built based on historical action trajectories;

[0007] Based on the knowledge graph, the target attribute information of the target action trajectory is determined, and the target attribute information is used as the quality evaluation result of the target action trajectory.

[0008] According to another aspect of the present disclosure, a trajectory quality evaluation device based on a knowledge graph is provided, comprising:

[0009] a determination module, configured to determine, in response to a trajectory query request, a target action trajectory corresponding to the trajectory query request;

[0010] The acquisition module is used to obtain the knowledge graph pre-built based on historical action trajectories;

[0011] The evaluation module is used to determine the target attribute information of the target action trajectory based on the knowledge graph, and use the target attribute information as the quality evaluation result of the target action trajectory.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to cause a computer to execute the method in any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method in any embodiment of the present disclosure when executed by a processor.

[0018] This disclosure provides a trajectory quality evaluation method, device, and electronic device based on a knowledge graph. A knowledge graph is pre-built based on historical motion trajectories. Based on the knowledge graph, target attribute information for a target motion trajectory corresponding to a trajectory query request is determined as the target motion trajectory quality evaluation result. Obtaining the target motion trajectory quality evaluation result from the knowledge graph is low-cost, interpretable, and can meet dynamic query requirements. By evaluating the quality of motion trajectories, the utilization rate of motion trajectories can be effectively improved.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0021] Figure 1 Flowchart of a trajectory quality evaluation method based on knowledge graph in one embodiment of the present disclosure;

[0022] Figure 2 A schematic diagram of the mapping relationship between data source nodes and user nodes in an embodiment of the present disclosure;

[0023] Figure 3 Flowchart of a trajectory quality evaluation method based on knowledge graph in one embodiment of the present disclosure;

[0024] Figure 4 Schematic diagram of a trajectory quality evaluation device based on a knowledge graph in one embodiment of the present disclosure;

[0025] Figure 5 This is a block diagram of an electronic device used to implement the knowledge graph-based trajectory quality evaluation method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0027] The present disclosure provides a trajectory quality evaluation method based on knowledge graph. Figure 1 This is a flowchart of a trajectory quality evaluation method based on a knowledge graph according to an embodiment of the present disclosure. The method can be applied to a trajectory quality evaluation device based on a knowledge graph. For example, when the device is deployed on a terminal or server or other processing device, it can perform trajectory quality evaluation, etc. The terminal can be a user equipment (UE), a mobile device, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the method can also be implemented by a processor calling computer-readable instructions stored in a memory. For example Figure 1 As shown, including:

[0028] Step S101, in response to a trajectory query request, determining a target action trajectory corresponding to the trajectory query request;

[0029] In this embodiment, the server is the execution body. The server receives the trajectory query request, parses the trajectory query request, and determines the target action trajectory that meets the trajectory query request from the historical action trajectory of the user using the electronic map based on the parsed result.

[0030] The historical action trajectory can be the action trajectory of the user when using the electronic map obtained by the mobile terminal, and each point in the action trajectory can be the user's location information obtained by the positioning module of the mobile terminal. The target action trajectory can be one or more.

[0031] Step S102: obtaining a knowledge graph pre-built based on historical action trajectories;

[0032] A knowledge graph is constructed and stored in advance based on the historical action trajectories of a large number of users. After receiving a trajectory query request, the pre-stored knowledge graph is called for query.

[0033] Step S103: Determine target attribute information of the target action trajectory based on the knowledge graph, and use the target attribute information as a quality evaluation result of the target action trajectory.

[0034] Because knowledge graphs have reasoning capabilities, they can obtain more valuable target attribute information, which can be used as the quality evaluation result of the target's action trajectory, achieving effective evaluation of the target's action trajectory. The target attribute information can be single or multiple. Based on this target attribute information, high-quality action trajectories can be identified and provided to other data sources for use, thereby improving the utilization of action trajectories.

[0035] Related technologies directly collect statistics on the attribute information of movement trajectories to generate statistical reports as the evaluation results of movement trajectories. However, evaluating movement trajectories based on statistical reports has certain drawbacks. For example, only the characteristics of the movement trajectories of all users from source A can be statistically analyzed. Switching to individual users or switching to different attributes is costly, for example, switching between user X from source A and user Y from source A, or switching between city P from source A and city Q from source A. This requires regenerating statistical reports for all data, which is costly. Moreover, if the quality of movement trajectories from a particular source improves, it is unclear whether the improvement is due to improved trajectory quality in a particular city or an increase in the mileage ratio of certain high-quality users. This makes the quality evaluation results less interpretable. However, querying through a knowledge graph can obtain target attribute information based on the query request for users to review, thus clarifying the reasons for the improvement in trajectory quality. Furthermore, quality evaluation based on statistical reports only has one statistical report with fixed results, which cannot support dynamic queries. However, querying through a knowledge graph allows for dynamic queries based on demand. Moreover, it is impossible to query attribute information within a preset time range (for example, daily, weekly, monthly, etc.) through statistical reports. However, knowledge graphs can meet various query needs and enable users to perceive the differences between various action trajectories in a three-dimensional way.

[0036] The knowledge graph-based trajectory quality evaluation method provided by the disclosed embodiments pre-constructs a knowledge graph based on historical action trajectories. Based on the knowledge graph, the target attribute information of the target action trajectory corresponding to the trajectory query request is determined as the target action trajectory quality evaluation result. Obtaining the target action trajectory quality evaluation result through the knowledge graph is low-cost, interpretable, and can meet dynamic query requirements. By performing quality evaluation on action trajectories, the utilization rate of action trajectories can be effectively improved.

[0037] The technical solution disclosed herein also includes a process of constructing a knowledge graph, as shown in the following embodiments:

[0038] In a possible implementation, the method further includes:

[0039] Pre-acquire first attribute information corresponding to the data source node, second attribute information corresponding to the user node, and an association relationship between the first attribute information and the second attribute information;

[0040] Constructing a knowledge graph based on the first attribute information, the second attribute information, and the association relationship;

[0041] The first attribute information is used to characterize the attributes of the historical action trajectory corresponding to the data source node; the second attribute information is used to characterize the attributes of the historical action trajectory corresponding to the user node.

[0042] In practical applications, attribute information of a user's historical movement trajectory is obtained to construct a knowledge graph. A knowledge graph includes two types of nodes: data source nodes and user nodes. Attribute information can include attribute values corresponding to attributes. Historical movement trajectories include historical movement trajectories of users from different data sources. The first attribute information corresponding to a data source node characterizes the attributes of the historical movement trajectories of multiple users corresponding to the data source node. For example, if application A is a data source node, the first attribute information corresponding to the data source node characterizes the attributes of the movement trajectories generated by multiple users using application A while also using an electronic map. The second attribute information characterizes the attributes of the historical movement trajectories of the users corresponding to the user node. For example, the attribute information of the movement trajectories of users using an electronic map. The association between the first attribute information and the second attribute information can be a one-to-many mapping relationship between a data source and the corresponding users. For example, if users U1 and U2 use application A, application A is considered a data source node, and users U1 and U2 are considered user nodes. A one-to-many mapping relationship is established between application A and users U1 and U2, with edges between the data source node and the two user nodes, respectively.

[0043] Among them, the first attribute information and the second attribute information include but are not limited to: node identification information, Chinese name, city, user mileage, average single mileage, point-by-point mileage, user duration, average single duration, point-by-point duration, average confidence, average vehicle probability, average output probability (emission probability), average projection distance (projection distance represents the distance the trajectory point is projected onto the road), average speed, maximum speed, trajectory evaluation, whether it is a truck, whether it is a tram, etc.

[0044] Figure 2 Schematic diagram of the mapping relationship between data source nodes and user nodes in the embodiment of the present disclosure. Figure 2 As shown, the data source node and each user node have a one-to-many mapping relationship. Figure 2 , it is shown that one data source node and seven user nodes have an association relationship.

[0045] In the embodiment of the present disclosure, a knowledge graph is constructed using the attribute information of the historical action trajectories corresponding to the data source nodes and user nodes, as well as the association relationships. The knowledge graph obtained in this way can be used for trajectory query, and the trajectory quality evaluation can be performed based on the attribute information obtained from the query.

[0046] In a possible implementation, the method further includes:

[0047] If the first attribute information includes first default attribute information, and the second attribute information includes first real attribute information, determining the second real attribute information based on the first real attribute information and a preconfigured first inference rule;

[0048] The first default attribute information is replaced by the second real attribute information.

[0049] The first attribute information is the attribute information of the data source node, that is, the attribute value of the attribute of the data source node. The first attribute information may include first default attribute information, which may be an initial value pre-configured for the data source node, for example, -1.

[0050] The second attribute information is the attribute information of the user node, that is, the attribute value of the user node. The second attribute information may include the first real attribute information, which may be a real value obtained by statistically calculating the user's trajectory. For example, if a user has multiple historical movement trajectories, the mileage of each historical movement trajectory of the user can be summed to obtain the user mileage corresponding to the user as the real attribute information.

[0051] The attribute information of a data source node can be calculated using the attribute information of the user nodes associated with the data source node using a preconfigured first inference rule. The first inference rule can be configured based on specific needs. For example, if data source node a1 corresponds to three user nodes, X, Y, and Z, then the total mileage of data source node a1 is equal to the sum of the mileages of the three user nodes, X, Y, and Z; the maximum speed of data source node a1 is equal to the maximum speed of the three user nodes, X, Y, and Z; and the average confidence of data source node a1 is equal to the average of the average confidences of the three user nodes, X, Y, and Z.

[0052] In the embodiment of the present disclosure, the attribute value of the data source node can be calculated based on the attribute information of the associated user node, and the calculated true value is used to replace the preconfigured default value to obtain the true value of the attribute information of the data source node.

[0053] In a possible implementation, the method further includes:

[0054] If the first attribute information includes third real attribute information, and the second attribute information includes second default attribute information, determining fourth real attribute information based on the third real attribute information and a preconfigured second inference rule;

[0055] The second default attribute information is replaced by the fourth real attribute information.

[0056] The third real attribute information may be the real attribute information of the data source node calculated based on the real attribute information of multiple user nodes, and the second attribute information may be the preconfigured default attribute information of the user node, for example, -1. If the real attribute information of a user node cannot be directly obtained, it can be inferred based on the data source node corresponding to the user node and the preconfigured second inference rule, and the default attribute information can be replaced with the real attribute information.

[0057] For example, based on the true values of the attribute information of most users associated with the data source node, it is determined that the attribute value of the attribute "Is it a truck" is the true value 1. Then for a user associated with the data source node, if the attribute value of the user's attribute "Is it a truck" is the default attribute value -1, the -1 can be replaced according to the true attribute value of the data source node, thereby obtaining the true attribute value 1 of the attribute "Is it a truck" of the user node.

[0058] In the embodiment of the present disclosure, the attribute value of the user node can be calculated based on the attribute information of the associated data source node, and the preconfigured default value can be replaced with the calculated real value to obtain the real value of the attribute information of the user node.

[0059] In a possible implementation, the method further includes:

[0060] If the first attribute information includes first default attribute information and at least one fifth real attribute information;

[0061] determining sixth real attribute information based on at least one fifth real attribute information and a preconfigured third inference rule;

[0062] The first default attribute information is replaced by the sixth real attribute information.

[0063] In actual applications, if the attribute values of some of the multiple attributes of a data source node are real attribute values, and the attribute values of another part of the attributes are default attribute values, the real attribute values of the other part of the attributes can be calculated based on the real attribute values of the part of the attributes of the data source node and the preconfigured third inference rule.

[0064] For example, if the data source node attributes "emission probability," "confidence," and "movement probability" are true attribute values, and the attribute "trajectory evaluation" is the default attribute value, the true attribute value of the attribute "trajectory evaluation" can be obtained based on the true attribute values of "emission probability," "confidence," and "movement probability" and the preconfigured third inference rule. This true attribute value can be a distributed value between 0 and 1, and the default attribute value of "trajectory evaluation" can be replaced with the true value. For the "trajectory evaluation" attribute, it can be assumed that the larger the attribute value, the better the quality of the action trajectory.

[0065] In the embodiment of the present disclosure, the real attribute values of a part of the attributes of the data source node and the preconfigured third inference rule can be calculated to replace the default attribute values, thereby obtaining all the real attribute values of the data source node.

[0066] In a possible implementation, the method further includes:

[0067] If there are multiple target motion trajectories and each target motion trajectory has multiple target attribute information, a target attribute report is generated using the target attribute information of the multiple target motion trajectories. The target attribute report is used to evaluate the multiple target motion trajectories.

[0068] In practical applications, if, based on a trajectory query request, it is determined that the query request corresponds to multiple target action trajectories, and multiple target attribute information of each target action trajectory is obtained based on the knowledge graph, the attribute information of each target action trajectory can be displayed in the form of a generated report. For example, each row in the report displays multiple target attribute information of a target action trajectory, which can be the target attribute information of target action trajectories from different data sources. Each column in the report displays the attribute information of the same attribute of different target action trajectories. The attribute information of the same attribute is different, so that the differences in action trajectories from different data sources can be displayed through the target attribute report.

[0069] In the embodiment of the present disclosure, target attribute information of multiple target action trajectories is generated and displayed in a target attribute report, so that the evaluation result can be made more intuitive.

[0070] In one possible implementation, in response to a trajectory query request, determining a target action trajectory corresponding to the trajectory query request includes:

[0071] Parse the trajectory query request to obtain the query conditions;

[0072] According to the query conditions, the target action trajectory corresponding to the trajectory query request is determined.

[0073] In actual applications, after receiving a trajectory query request, the request is parsed. Based on the parsed results, query conditions are obtained. One or more target trajectories that meet the query conditions are identified. Then, one or more target attribute information for each target trajectory is obtained based on the knowledge graph. For example, the query condition could be the user mileage of the trajectory corresponding to the data source node in city P, with a confidence greater than x and a projection distance less than y. After identifying the target trajectories that meet the query conditions, the user mileage of the target trajectory is determined based on the knowledge graph. Attribute information such as trajectory evaluation can also be included as the evaluation result of the target trajectory.

[0074] In the embodiment of the present disclosure, according to the trajectory query request, the target action trajectory that meets the user's needs can be obtained, and then the target attribute information can be determined through the knowledge graph to achieve the quality evaluation of the target action trajectory.

[0075] Figure 3 Flowchart of a trajectory quality evaluation method based on knowledge graph in one embodiment of the present disclosure.

[0076] like Figure 3 As shown, the method includes:

[0077] Step S301: Acquire first attribute information corresponding to a data source node, second attribute information corresponding to a user node, and an association relationship between the first attribute information and the second attribute information;

[0078] Step S302: construct a knowledge graph based on the first attribute information, the second attribute information, and the association relationship; wherein the first attribute information is used to characterize the attributes of the historical action trajectory corresponding to the data source node; and the second attribute information is used to characterize the attributes of the historical action trajectory corresponding to the user node.

[0079] Step S303: receiving a trajectory query request, parsing the trajectory query request, and obtaining query conditions;

[0080] Step S304: determining the target action trajectory corresponding to the trajectory query request according to the query condition.

[0081] Step S305: Obtain a knowledge graph pre-constructed based on historical action trajectories.

[0082] Step S306: Determine target attribute information of the target action trajectory based on the knowledge graph, and use the target attribute information as a quality evaluation result of the target action trajectory.

[0083] The knowledge graph-based trajectory quality evaluation method provided by the disclosed embodiments pre-constructs a knowledge graph based on historical action trajectories. Based on the knowledge graph, the target attribute information of the target action trajectory corresponding to the trajectory query request is determined as the target action trajectory quality evaluation result. Obtaining the target action trajectory quality evaluation result through the knowledge graph is low-cost, interpretable, and can meet dynamic query requirements. By performing quality evaluation on action trajectories, the utilization rate of action trajectories can be effectively improved.

[0084] Figure 4 Schematic diagram of a trajectory quality evaluation device based on a knowledge graph in one embodiment of the present disclosure. Figure 4 As shown, the trajectory quality evaluation device based on the knowledge graph may include:

[0085] A determination module 401 is configured to determine, in response to a trajectory query request, a target action trajectory corresponding to the trajectory query request;

[0086] Acquisition module 402, used to acquire a knowledge graph pre-built based on historical action trajectories;

[0087] The evaluation module 403 is used to determine target attribute information of the target action trajectory based on the knowledge graph, and use the target attribute information as the quality evaluation result of the target action trajectory.

[0088] The knowledge graph-based trajectory quality evaluation device provided in the disclosed embodiments pre-builds a knowledge graph based on historical action trajectories. Based on the knowledge graph, it determines the target attribute information of the target action trajectory corresponding to the trajectory query request, which serves as the target action trajectory quality evaluation result. Obtaining the target action trajectory quality evaluation result through the knowledge graph is low-cost, interpretable, and can meet dynamic query requirements. By performing quality evaluation on action trajectories, the utilization rate of action trajectories can be effectively improved.

[0089] In a possible implementation, the apparatus further includes a building module configured to:

[0090] Pre-acquire first attribute information corresponding to the data source node, second attribute information corresponding to the user node, and an association relationship between the first attribute information and the second attribute information;

[0091] Constructing a knowledge graph based on the first attribute information, the second attribute information, and the association relationship;

[0092] The first attribute information is used to characterize the attributes of the historical action trajectory corresponding to the data source node; the second attribute information is used to characterize the attributes of the historical action trajectory corresponding to the user node.

[0093] In a possible implementation, the apparatus further includes a first reasoning module configured to:

[0094] If the first attribute information includes first default attribute information, and the second attribute information includes first real attribute information, determining the second real attribute information based on the first real attribute information and a preconfigured first inference rule;

[0095] The first default attribute information is replaced by the second real attribute information.

[0096] In a possible implementation, the apparatus further includes a second reasoning module, configured to:

[0097] If the first attribute information includes third real attribute information, and the second attribute information includes second default attribute information, determining fourth real attribute information based on the third real attribute information and a preconfigured second inference rule;

[0098] The second default attribute information is replaced by the fourth real attribute information.

[0099] In a possible implementation, the apparatus further includes a third reasoning module, configured to:

[0100] If the first attribute information includes first default attribute information and at least one fifth real attribute information;

[0101] determining sixth real attribute information based on at least one fifth real attribute information and a preconfigured third inference rule;

[0102] The first default attribute information is replaced by the sixth real attribute information.

[0103] In a possible implementation, the apparatus further includes a generating module configured to:

[0104] If there are multiple target motion trajectories and each target motion trajectory has multiple target attribute information, a target attribute report is generated using the target attribute information of the multiple target motion trajectories. The target attribute report is used to evaluate the multiple target motion trajectories.

[0105] In a possible implementation, the determining module 401 is specifically configured to:

[0106] Parse the trajectory query request to obtain the query conditions;

[0107] According to the query conditions, the target action trajectory corresponding to the trajectory query request is determined.

[0108] The functions of each unit, module or sub-module in each device of the embodiments of the present disclosure can be found in the corresponding description in the above method embodiments, and will not be repeated here.

[0109] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0110] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0111] at least one processor; and

[0112] a memory communicatively connected to the at least one processor; wherein,

[0113] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0114] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to cause a computer to execute the method in any embodiment of the present disclosure.

[0115] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the method in any embodiment of the present disclosure when executed by a processor.

[0116] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0117] like Figure 5 As shown, the device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and information required for the operation of the device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0118] Various components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0119] The computing unit 501 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the knowledge graph-based trajectory quality assessment method. For example, in some embodiments, the knowledge graph-based trajectory quality assessment method can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the knowledge graph-based trajectory quality assessment method described above can be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the knowledge graph-based trajectory quality evaluation method in any other appropriate manner (for example, by means of firmware).

[0120] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive information and instructions from a storage system, at least one input device, and at least one output device, and transmit information and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable information processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as an information server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital information communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0125] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0126] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0127] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A trajectory quality evaluation method based on a knowledge graph, the method comprising: In response to a trajectory query request, determining a target movement trajectory corresponding to the trajectory query request; Obtain a knowledge graph pre-built based on historical action trajectories; Determining target attribute information of the target action trajectory based on the knowledge graph, and using the target attribute information as a quality evaluation result of the target action trajectory; The construction method of the knowledge graph includes: Pre-acquire first attribute information corresponding to a data source node, second attribute information corresponding to a user node, and an association relationship between the first attribute information and the second attribute information; Constructing a knowledge graph based on the first attribute information, the second attribute information, and the association relationship; The first attribute information is used to represent the attribute of the historical action trajectory corresponding to the data source node; the second attribute information is used to represent the attribute of the historical action trajectory corresponding to the user node.

2. The method according to claim 1, wherein Also includes: If the first attribute information includes first default attribute information, and the second attribute information includes first real attribute information, determining second real attribute information based on the first real attribute information and a preconfigured first inference rule; The first default attribute information is replaced by the second real attribute information.

3. The method according to claim 1, further comprising: If the first attribute information includes third real attribute information, and the second attribute information includes second default attribute information, determining fourth real attribute information based on the third real attribute information and a preconfigured second inference rule; The second default attribute information is replaced by the fourth real attribute information.

4. The method according to claim 1, further comprising: If the first attribute information includes first default attribute information and at least one fifth real attribute information; determining sixth real attribute information based on the at least one fifth real attribute information and a preconfigured third inference rule; The first default attribute information is replaced by the sixth real attribute information.

5. The method according to any one of claims 1 to 4, further comprising: If there are multiple target motion trajectories and each target motion trajectory has multiple target attribute information, a target attribute report is generated using the target attribute information of the multiple target motion trajectories. The target attribute report is used to evaluate the multiple target motion trajectories.

6. The method according to any one of claims 1 to 4, wherein: The step of determining, in response to the trajectory query request, a target movement trajectory corresponding to the trajectory query request, includes: Parsing the trajectory query request to obtain query conditions; Determine the target action trajectory corresponding to the trajectory query request according to the query condition.

7. A trajectory quality evaluation device based on a knowledge graph, the device comprising: a determination module, configured to determine, in response to a trajectory query request, a target movement trajectory corresponding to the trajectory query request; The acquisition module is used to obtain the knowledge graph pre-built based on historical action trajectories; an evaluation module, configured to determine target attribute information of the target action trajectory based on the knowledge graph, and use the target attribute information as a quality evaluation result of the target action trajectory; Building blocks for: Pre-acquire first attribute information corresponding to a data source node, second attribute information corresponding to a user node, and an association relationship between the first attribute information and the second attribute information; Constructing a knowledge graph based on the first attribute information, the second attribute information, and the association relationship; The first attribute information is used to represent the attribute of the historical action trajectory corresponding to the data source node; the second attribute information is used to represent the attribute of the historical action trajectory corresponding to the user node.

8. The device according to claim 7, wherein Also included is a first reasoning module, configured to: If the first attribute information includes first default attribute information, and the second attribute information includes first real attribute information, determining second real attribute information based on the first real attribute information and a preconfigured first inference rule; The first default attribute information is replaced by the second real attribute information.

9. The apparatus according to claim 7, further comprising a second reasoning module, configured to: If the first attribute information includes third real attribute information, and the second attribute information includes second default attribute information, determining fourth real attribute information based on the third real attribute information and a preconfigured second inference rule; The second default attribute information is replaced by the fourth real attribute information.

10. The apparatus according to claim 7, further comprising a third reasoning module, configured to: If the first attribute information includes first default attribute information and at least one fifth real attribute information; determining sixth real attribute information based on the at least one fifth real attribute information and a preconfigured third inference rule; The first default attribute information is replaced by the sixth real attribute information.

11. The apparatus according to any one of claims 7 to 10, further comprising a generating module configured to: If there are multiple target motion trajectories and each target motion trajectory has multiple target attribute information, a target attribute report is generated using the target attribute information of the multiple target motion trajectories. The target attribute report is used to evaluate the multiple target motion trajectories.

12. The device according to any one of claims 7 to 10, wherein: The determining module is specifically configured to: Parsing the trajectory query request to obtain query conditions; Determine the target action trajectory corresponding to the trajectory query request according to the query condition.

13. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images