Wireless interference detection method and apparatus, storage medium, and electronic device
Quadruple information is extracted through the wireless interference detection intention and interference intention detection elements input by the user, and combined with the wireless interference detection knowledge graph to generate an atomic rule detection sequence, solving the problem that users cannot flexibly adjust the detection workflow, and achieving flexible adjustment and improved management The effect of efficiency.
Patent Information
- Application Number
- PCT/CN2023/143632
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-21
- Filing Date
- 2023-12-29
- Publication Date
- 2024-12-26
AI Technical Summary
In telecommunications network management, interference detection of wireless cells is usually periodically performed using AI or rule algorithms, and users cannot flexibly adjust the detection workflow according to the detection results and requirements.
Quadruple information is extracted through the wireless interference detection intention and interference intention detection elements input by the user, adapt to the atomic rule detection sequence based on the pre-constructed wireless interference detection knowledge graph, wireless interference detection is performed, and detection results are output.
The ability to flexibly adjust the detection workflow according to the wireless interference detection results and requirements is realized, and the flexibility of detection and management efficiency is improved.
Smart Images

Figure CN2023143632_26122024_PF_FP_ABST
Abstract
Description
Wireless interference detection method and device, storage medium and electronic device
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application is based on Chinese patent application CN202310747809.X, filed on June 21, 2023, entitled “Wireless Interference Detection Method and Device, Storage Medium and Electronic Device”, and claims the priority of the patent application. All the disclosed contents are incorporated into this application by reference. Technical Field
[0003] The embodiments of the present disclosure relate to the field of communications, and in particular, to a wireless interference detection method and device, a storage medium, and an electronic device. Background Art
[0004] In telecommunications network management, interference detection in wireless cells is often performed periodically using AI or rule-based algorithms. The detection process is a predefined workflow, and the system outputs analysis results after detection. Parameters such as the time and target for initiating the interference detection task must be manually specified. Furthermore, users cannot flexibly adjust the interference detection workflow based on detection results and requirements.
[0005] Summary of the Invention
[0006] The embodiments of the present disclosure provide a wireless interference detection method and device, a storage medium, and an electronic device to at least solve the problem in related technologies that users cannot flexibly adjust the workflow of wireless interference detection according to wireless interference detection results and requirements.
[0007] According to one embodiment of the present disclosure, a wireless interference detection method is provided, including: extracting four-tuple information for wireless interference detection based on wireless interference detection intention and interference intention detection elements input by a user; determining an atomic rule detection sequence adapted to a pre-constructed wireless interference detection knowledge graph based on the four-tuple information; performing wireless interference detection according to the atomic rule detection sequence, and outputting the wireless interference detection result.
[0008] According to another embodiment of the present disclosure, a wireless interference detection device is provided, including: an interference detection intention engine module, configured to extract four-tuple information for wireless interference detection based on the wireless interference detection intention and interference intention detection elements input by the user; an interference detection algorithm processing module, configured to determine an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph based on the four-tuple information; an interference detection processing execution module, configured to perform wireless interference detection according to the atomic rule detection sequence, and output a wireless interference detection result.
[0009] According to another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.
[0010] According to another embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] FIG1 is a hardware structure block diagram of a computer terminal of a wireless interference detection method according to an embodiment of the present disclosure;
[0012] FIG2 is a flow chart of a wireless interference detection method according to an embodiment of the present disclosure;
[0013] FIG3 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure;
[0014] FIG4 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure;
[0015] FIG5 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure;
[0016] FIG6 is a schematic diagram of the architecture of a wireless interference detection device according to an embodiment of the present disclosure;
[0017] FIG7 is a flow chart of a wireless interference detection method according to an embodiment of the present disclosure;
[0018] FIG8 is a flow chart showing the principle of generating an atomic rule detection sequence from a knowledge graph according to an embodiment of the disclosed scenario. DETAILED DESCRIPTION
[0019] Hereinafter, the embodiments of the present disclosure will be described in detail with reference to the accompanying drawings and in combination with the embodiments.
[0020] It should be noted that the terms "first", "second", etc. in the description and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.
[0021] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 is a hardware structure block diagram of a computer terminal of a wireless interference detection method according to an embodiment of the present disclosure. As shown in Figure 1, the computer terminal may include one or more (only one is shown in Figure 1) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that the structure shown in Figure 1 is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than those shown in Figure 1, or have a configuration different from that shown in Figure 1.
[0022] The memory 104 can be used to store computer programs, such as software programs and modules of application software, such as the computer program corresponding to the wireless interference detection method in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-mentioned method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0023] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a communications provider of a computer terminal. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0024] In this embodiment, a wireless interference detection method running on the above-mentioned computer terminal is provided. FIG2 is a flow chart of the wireless interference detection method according to an embodiment of the present disclosure. As shown in FIG2 , the flow chart includes the following steps:
[0025] Step S202: extracting four-tuple information for wireless interference detection based on the wireless interference detection intention and interference intention detection elements input by the user;
[0026] In an exemplary embodiment, interference intention conflict detection includes at least one of the following: whether wireless interference detection resources conflict; whether wireless interference detection function scenarios conflict; whether execution time of wireless interference detection intention conflicts.
[0027] In actual implementation, the wireless interference detection intention input by the user may be in text form or voice form.
[0028] In an exemplary embodiment, the four-tuple information includes: object or area information of wireless interference detection, time information of wireless interference detection, action information of wireless interference detection, and presentation method information of wireless interference detection results.
[0029] In an exemplary embodiment, after extracting the four-tuple information used for wireless interference detection based on the wireless interference detection intention and interference intention detection elements input by the user, it also includes: confirming the integrity and legality of the content in the four-tuple information; performing interference intention conflict detection on the four-tuple information based on the interference intention detection elements, and adjusting the four-tuple information whose detection result of the interference intention conflict detection is a conflict according to a preset conflict resolution strategy.
[0030] In actual implementation, interference detection intent testing involves both validity and conflict detection. This validation includes ensuring that the translated user intent contains four elements; the objects included in the four elements must exist, and the detailed information must be valid. Conflict detection includes resource conflicts, interference detection function scenario conflicts, and interference detection intent execution time conflicts. The validity and conflict detection modules use a specified resolution strategy, either automatically or interactively, to resolve the conflict, ultimately outputting a conflict-free intent task and sending the task containing the user intent information to the interference detection algorithm processing center.
[0031] Step S204: determining an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph based on the four-tuple information;
[0032] In an exemplary embodiment, a pre-built wireless interference detection knowledge graph includes at least data entities and entity relationships between data entities, wherein the data entities include at least one of the following: supported standards for wireless interference detection, detection rules for wireless interference detection, configuration data of objects for wireless interference detection, engineering parameters of objects for wireless interference detection, performance counters or key performance indicators; and the entity relationships include at least one of the following: inclusion relationship, usage relationship, and dependency relationship.
[0033] In an exemplary embodiment, an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph is determined based on quadruple information, including: determining a rule sequence supported by the wireless interference detection knowledge graph based on the quadruple information; obtaining a list of atomic rules in the entity rules of the wireless interference detection knowledge graph according to the entity relationship in the rule sequence; and arranging the atomic rule list into an atomic rule detection sequence according to a preset strategy order.
[0034] In actual implementation, the interference detection algorithm processing center combines the interference detection knowledge graph to generate an atomic rule detection sequence, including data query, initial candidate cell screening, expert rules or AI detection, and segmented detection. Based on the command object / region and action, the algorithm processing center adapts and specifies the object corresponding to the knowledge graph rule, and uses the knowledge graph to generate the atomic rule detection sequence.
[0035] Step S206: Perform wireless interference detection according to the atomic rule detection sequence, and output the wireless interference detection result.
[0036] In an exemplary embodiment, wireless interference detection is performed according to an atomic rule detection sequence, including: filling the atomic rule detection sequence according to the wireless interference detection intention to obtain an interference detection atomic rule detection workflow; and performing wireless interference detection according to the interference detection atomic rule detection workflow.
[0037] During the actual implementation process, the commands in the atomic rule detection sequence set are expanded and filled with detailed information: for each atomic rule command, based on the information entered for this intention ([object] or [region], configuration data, project parameters or performance counters / KPIs), the number of atomic rule detections and the specific information of the data entities in the rule are expanded or filled.
[0038] In an exemplary embodiment, after performing wireless interference detection according to the atomic rule detection sequence and outputting the wireless interference detection results, it also includes: evaluating the wireless interference detection results, and adjusting the entities and entity relationships of the pre-built interference detection knowledge graph according to the evaluation results, and the adjustment method includes at least one of the following: adding new entities and entity relationships, modifying entities and entity relationships, and deleting entities and entity relationships.
[0039] During implementation, the algorithm processing center analyzes and evaluates the detection results reported by the algorithm processing center, obtaining metrics including, but not limited to, the accuracy of interference types, the accuracy of unknown interference segmentation, and the accuracy of interfering cell locations. These metrics are then visualized to optimize the interference detection knowledge graph. The intent closed-loop module leverages the interference detection knowledge graph module to adjust, optimize, and / orchestrate entities and entity relationships. This module adjusts existing entities and entity relationships, adds and deletes new knowledge graph rule entities and entity relationships, and adjusts, expands, and orchestrates the interference detection knowledge graph.
[0040] Through the above steps, four-tuple information for wireless interference detection is extracted based on the wireless interference detection intent and interference intent detection elements input by the user; an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph is determined based on the four-tuple information; wireless interference detection is performed according to the atomic rule detection sequence, and the wireless interference detection result is output. Through the embodiments of the present disclosure, the problem in related technologies where users cannot flexibly adjust the wireless interference detection workflow based on wireless interference detection results and requirements is solved, and the wireless interference detection workflow can be flexibly adjusted based on the wireless interference detection results and requirements.
[0041] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the embodiment of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD-ROM), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the method described in the embodiment of the present disclosure.
[0042] This embodiment also provides a wireless interference detection device for implementing the above-mentioned embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.
[0043] Figure 3 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure. As shown in Figure 3, the detection device 30 includes: an interference detection intention engine module 310, which is used to extract four-tuple information for wireless interference detection based on the wireless interference detection intention and interference intention detection elements input by the user; an interference detection algorithm processing module 320, which is used to determine an atomic rule detection sequence that is adapted to a pre-built wireless interference detection knowledge graph based on the four-tuple information; and an interference detection processing execution module 330, which is used to perform wireless interference detection according to the atomic rule detection sequence and output the wireless interference detection result.
[0044] In an exemplary embodiment, the interference detection algorithm processing module 320 may include: a determination unit for determining a rule sequence supported by the wireless interference detection knowledge graph based on quadruple information; an acquisition unit for acquiring an atomic rule list in the entity rules of the wireless interference detection knowledge graph based on the entity relationship in the rule sequence; and a sorting unit for organizing the atomic rule list into an atomic rule detection sequence according to a preset strategy order.
[0045] In an exemplary embodiment, the interference detection processing execution module 330 may include: a filling unit for filling the atomic rule detection sequence according to the wireless interference detection intention to obtain an interference detection atomic rule detection workflow; a detection unit for performing wireless interference detection according to the interference detection atomic rule detection workflow.
[0046] Figure 4 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure. As shown in Figure 4, in addition to all the modules shown in Figure 3, the detection device 40 also includes: an interference detection intention management module 410, which is used to confirm the integrity and legality of the content in the four-tuple information, and perform interference intention conflict detection on the four-tuple information based on the interference intention detection elements, so as to adjust the four-tuple information whose detection result of the interference intention conflict detection is a conflict according to a preset conflict resolution strategy.
[0047] Figure 5 is a structural block diagram of a wireless interference detection device according to an embodiment of the present disclosure. As shown in Figure 5, in addition to all the modules shown in Figure 4, the detection device 50 also includes: an interference detection intention closed-loop module 510, which is used to evaluate the wireless interference detection results and adjust the entities and entity relationships of the pre-built interference detection knowledge graph according to the evaluation results. The adjustment method includes at least one of the following: adding new entities and entity relationships, modifying entities and entity relationships, and deleting entities and entity relationships.
[0048] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.
[0049] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.
[0050] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.
[0051] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0052] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0053] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.
[0054] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present disclosure can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented using program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be made into individual integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module for implementation. Thus, the embodiments of the present disclosure are not limited to any specific combination of hardware and software.
[0055] In order to enable those skilled in the art to better understand the technical solutions of the embodiments of the present disclosure, the following is an elaboration with reference to specific scenario embodiments.
[0056] Scenario Example 1
[0057] The disclosed embodiment starts from the perspective of intent-driven and knowledge graph, and drives the command issuance, parameter setting and result output in interference detection in an intention-driven manner, and automatically assembles the detection workflow for detection based on the detection knowledge graph. It also provides the adjustment and arrangement functions of the knowledge graph for users to flexibly optimize and adjust. The detection intention can instruct the system what to do and the goals to be achieved without instructing the system how to do it. Users who adopt the technical method of this application only need to reflect / indicate the goal of interference detection through the detection intention, and the system can automatically assemble the interference detection instructions to form a workflow for interference detection and output the detection results, which can greatly improve management efficiency, enhance the flexibility of wireless interference detection and the ease of use of the system for users.
[0058] In an embodiment of the present disclosure, a wireless interference detection device is provided. FIG6 is an architectural schematic diagram of the wireless interference detection device according to an embodiment of the present disclosure. As shown in FIG6 , the device includes the following modules: an interference detection intention input and result output module, an interference detection intention engine module, an interference detection intention management module, an interference detection algorithm processing center module, an interference detection processing module, an interference detection knowledge graph, and an interference detection intention closed-loop module. In this embodiment of the scenario, the interference detection intention engine module in FIG6 can correspond to the interference detection intention engine module 310 in the above embodiment, the interference detection algorithm processing center module in FIG6 can correspond to the interference detection algorithm processing module 320 in the above embodiment, the interference detection processing module in FIG6 can correspond to the interference detection processing execution module 330 in the above embodiment, the interference detection intention management module in FIG6 can correspond to the interference detection intention management module 410 in the above embodiment, and the interference detection intention closed-loop module in FIG6 can correspond to the interference detection intention closed-loop module 510 in the above embodiment. In some specific embodiments, the functional divisions of the above modules may be different or repeated. The above is only an example and does not impose any specific restrictions on the module division and naming of the embodiments of the present disclosure. In actual implementation, as long as the wireless interference detection method of the embodiments of the present disclosure can be implemented, it will be sufficient.
[0059] In this scenario, the interference detection intent input and result output module is used to accept user interference detection intent input. For example, it can accept the following input: "Start interference detection for all SDR network element cells in subnet 8 at 6:00 every day, and display the detection results on a map." At the same time, the module also outputs the detection results based on the intent, such as visually presenting the location information of the interfering cells in a "map" format.
[0060] Interference detection intent engine module: This module structures the textual intent information into the four-tuple required by the interference detection function ([object] or [region], [time], [action], [presentation]).
[0061] For example, if the user enters the interference detection intent as "Start interference detection for all SDR cells in subnet 8 at 6:00 AM daily, and display the detection results on a map," the intent engine module outputs the following four-tuple: ([{Subnetwork, 6}, {NE,, SDR}, {Cells, all}}, {Everyday at 6:00 AM}, {Start}, {GIS}]). Table 1 provides a detailed description of the four-tuple information.
[0062] Table 1 Example of the contents of quadruple information
[0063] Interference Detection Intent Management Module: This module manages user interference detection command intents, including intent validity and intent conflict detection and resolution. This module detects the validity of intent inputs and conflicts between intent tasks (such as resource conflicts, overlapping detection objects between concurrent tasks, or task conflicts within detection time periods). It then resolves these conflicts automatically or interactively according to a specified resolution strategy, ultimately outputting a conflict-free intent task and sending the task containing the user's intent information to the interference detection algorithm processing center.
[0064] Interference detection knowledge graph: This knowledge graph reflects the knowledge entities and entity relationships related to various interference detection methods supported by the system. It allows the interference detection algorithm processing center to automatically assemble interference detection workflows based on specific intent inputs and this knowledge graph, and provides adjustment / optimization and orchestration functions for the intent detection closed-loop module to call to adjust / expand and optimize the knowledge graph.
[0065] The entities and attributes of the interference detection knowledge graph include but are not limited to the following information: supported formats, detection rules (including expert rules, AI, and presentation rules), configuration data, engineering parameters, performance counters or KPIs, etc.; as shown in Table 2, the relevant attributes of the interference detection entity are displayed.
[0066] Table 2 Examples of interference detection entities and attributes
[0067] Different interference detection knowledge graph entities also have different relationships, as shown in Table 3:
[0068] Table 3. Examples of entity relationships in the knowledge graph
[0069] The system provides interference detection knowledge graph adjustment, optimization, and orchestration capabilities. The system provides a default detection knowledge graph that defines the rule entities and entity relationships required for interference detection. The system also provides interference detection knowledge graph rule adjustment and orchestration capabilities, which the interference detection intent closed-loop module can call upon to adjust, optimize, and orchestrate entities and entity relationships.
[0070] Interference Detection Algorithm Processing Center: After obtaining the intent quadruple, this module combines the [object] or [area] and [action] in the quadruple with the interference knowledge graph, and obtains the supported rule sequence from the "supported formats" (identifiable by the object) and the "rules" used by the "supported formats" of the interference detection knowledge graph. Based on the entity relationships of these rules, the ItfDtAtomicRuleList atomic rule list in the entity rules is obtained. The algorithm processing center organizes these ItfDtAtomicRuleLists into an atomic rule detection sequence according to the pre-planned strategy sequence (such as the use and dependency order defined by the entity relationship). Finally, after expanding the atomic rule detection sequence and filling in the specific information based on the intent quadruple, it generates an interference detection atomic rule detection workflow and pushes it to the interference detection execution module for execution. The processing center reports the detection result data to the intent closed-loop module and the result output module.
[0071] Interference detection processing module: The interference detection processing module performs interference detection storage / merging and other processing according to the obtained rule sequence, executes it in sequence according to the atomic rule detection sequence, and returns the execution result data to the interference detection algorithm processing center module.
[0072] Interference Detection Intent Closed-Loop Module: This module monitors and collects detection result data from interference detection intent execution. The result data is reported to this intent closed-loop module by the processing center module. The interference detection intent closed-loop module analyzes the detection result data to obtain metrics including, but not limited to, interference type accuracy, unknown interference segmentation accuracy, and interference cell location accuracy, and evaluates the detection effectiveness after executing the interference detection workflow. Furthermore, based on the evaluation results, the intent closed-loop module invokes the adjustment, expansion, and orchestration functions of the knowledge graph module to adjust, expand, and optimize the entities and entity relationships defined in the interference detection knowledge graph to achieve better detection results.
[0073] Scenario Example 2
[0074] According to the wireless interference detection device provided in the first embodiment of the scenario, a wireless interference detection method is provided in the second embodiment of the scenario. FIG7 is a flow diagram of the wireless interference detection method according to the embodiment of the present disclosure. As shown in FIG7 , the wireless interference detection method includes the following steps:
[0075] Step S701 , the user inputs interference detection intention: the user inputs the intention according to the four elements required by the interference detection intention, and voice and natural language text input are supported.
[0076] Step S702 , interference detection intention translation, that is, finding four elements from the intention information input by the user, namely [object] or [region], [action], [time], and [presentation].
[0077] Step S703, interference detection intention detection: that is, interference detection intention legitimacy detection and conflict detection. Legitimate detection includes that the translated user intention must contain four elements; the objects contained in the four elements must exist, the detailed information must be legitimate, etc. Conflict detection includes resource conflicts, interference detection function scenario conflicts, interference detection intention execution time conflicts, etc. The legitimacy and conflict detection modules will solve the problem automatically or interactively according to the specified solution strategy, and finally output a conflict-free intention task, and send the task containing the user intention information to the interference detection algorithm processing center.
[0078] Step S704, sending to the interference detection algorithm processing center: sending the translated interference detection intention to the algorithm processing center.
[0079] Step S705: The interference detection algorithm processing center generates an atomic rule detection sequence. The interference detection algorithm processing center combines the interference detection knowledge graph to generate an atomic rule detection sequence, including data query, initial candidate cell screening, expert rule or AI detection, and segmented detection. Here, the algorithm processing center adapts and specifies the object corresponding to the knowledge graph rule based on the command object / region and action, and uses the knowledge graph to generate the atomic rule detection sequence.
[0080] FIG8 is a schematic diagram of a process for generating an atomic rule detection sequence from a knowledge graph according to an embodiment of the present disclosure, as shown in FIG8 , including:
[0081] In step S7051, the algorithm processing center obtains the intent quad, determines the object or action in the quad, and matches it with the supported formats and the ItfDtOperator of the rules used by the supported formats in the knowledge graph in the system to obtain the matching rule ItfDtRuleID.
[0082] In step S7052, the algorithm processing center obtains the rule corresponding to the ItfDtRuleID, finds other entities that are dependent or used in the entity relationship "dependence" or "use" in the knowledge graph, and obtains the ItfDtAtomicRuleList information.
[0083] Step S7053: The algorithm processing center processes the "dependency" or "use" information of the knowledge graph one by one: find the ItfDtAtomicRuleList that depends on a non-empty entity and the "use" entity;
[0084] In step S7054, the algorithm processing center combines the obtained ItfDtAtomicRuleList atomic rule detection commands into an atomic rule detection sequence. Here, the knowledge graph entity relationship definitions are traversed in dependency order to obtain a non-empty atomic rule detection sequence of ItfDtAtomicRuleList, thus obtaining an atomic rule detection sequence set.
[0085] In step S7055, the algorithm processing center expands and fills in detailed information on the commands in the atomic rule detection sequence set through objects or "used" entities: for each atomic rule command, based on the information entered for this intention ([object] or [region], configuration data, engineering parameters or performance counters / KPIs), the number of atomic rule detections and the specific information of the data entities in the rules are expanded or filled in.
[0086] For example, for the object {NodeB, 8} / action {start} in the intent input, the algorithm processing center will obtain all cells under NodeB8 (for example, 1, 2, 3, a total of 3 cells), expand the number of atomic rule detections (the number of cells), and then fill them into the expanded atomic rule configuration data objects {nodeb=8,cellid=1} / {nodeb=8,cellid=2} / {nodeb=8,cellid=3} to form a specific multiple atomic rule detection sequence.
[0087] Step S706 , the algorithm processing center pushes the atomic rule detection sequence to the interference detection processing module: after the atomic rule detection sequence is generated by the algorithm processing center, the algorithm processing center pushes the atomic rule detection sequence to the interference detection processing module.
[0088] In step S707, the algorithm processing center collects the interference detection result data and reports it to the intention closed-loop module and the intention input and result output module.
[0089] Step S708: The interference detection intention input and result output module "presents" the result according to the intention visualization.
[0090] Step S709: The intent closed-loop module optimizes the knowledge graph. Based on the result data reported by the algorithm processing center, the intent closed-loop module analyzes and evaluates the resulting data to obtain metrics, including but not limited to the accuracy of interference types, the accuracy of unknown interference segmentation, and the accuracy of interfering cell locations. It visualizes these metrics and optimizes the interference detection knowledge graph. The intent closed-loop module invokes the interference detection knowledge graph module to provide functions such as adjustment and optimization / orchestration of entities and entity relationships. This module adjusts existing entities and entity relationships, adds and deletes new knowledge graph rule entities and entity relationships, and adjusts, expands, and orchestrates the interference detection knowledge graph.
[0091] Specifically, the interference detection knowledge graph provides the following methods or approaches (including but not limited to the following steps) to adjust, expand, and arrange the knowledge graph:
[0092] (1) The system provides a knowledge graph adjustment and arrangement interface;
[0093] (2) The system presents the rule entities or data entities contained in the knowledge graph and the relationships between them in various friendly forms (such as graphics or lists, etc.), and provides an operation interface to add / delete / modify entities and adjust entity relationships; such as but not limited to the following operations: presenting operation buttons or menus such as "add", "modify", and "delete" for entities in a list or graphic, and providing the addition, deletion, and adjustment of entities. Presenting operation buttons or menus such as "add", "modify", and "delete" for entity relationships in a list or graphic, and providing the addition, deletion, and adjustment and optimization of entity relationships. Provide an easy-to-use method such as dragging and dropping connections between entities to directly add "add", "modify", and "delete" to adjust, optimize, and arrange the relationships between entities.
[0094] For example, for a preliminary screening rule in the atlas, Software Defined Radio Time Division Duplex (SDR TDD) interference detection only targets cells where the "carrier average noise interference (counter 373414597) value must be less than -120." The intent closed-loop module, based on the evaluated "cell interference location accuracy" indicator value, determines that the accuracy is insufficient and needs to expand the scope of collected cells. Therefore, it decides to adjust the value of the "carrier average noise interference (counter 373414597) value cannot be greater than -110" rule. In this case, the "SDR TDD preliminary screening" rule entity can be modified by adjusting its entity attribute ItfDtAtomicRuleList value to "373414597 <= -110."
[0095] For example, for the rule dependencies in the graph, the unknown segmentation rule "SDR-Unknown Segmentation Rule" depends on the results of the detection rule "Detection AI-CNN Algorithm". Based on the evaluated "Interference Type Accuracy" indicator value, the intention closed-loop module believes that it is necessary to add the detection rule "Detection AI-Clustering Algorithm" between the "SDR-Unknown Segmentation Rule" and the "Detection AI-CNN Algorithm". At this time, you can drag the relationship lines (entity relationship "dependence") between entities such as "SDR-Unknown Segmentation Rule", "Detection AI-Clustering Algorithm" and "Detection AI-CNN Algorithm" in the graph to adjust (arrange) the dependency between the three. In this way, in the subsequent generation of the interference detection workflow, the "Detection AI-CNN Algorithm" will be executed after the "Detection AI-Clustering Algorithm" rule is executed, and the "SDR-Unknown Segmentation Rule" will be executed only after the "Detection AI-Clustering Algorithm" is completed, thereby optimizing the interference detection workflow and improving the accuracy of the interference type.
[0096] The wireless interference detection method provided by the embodiments of the present disclosure allows users to input a user-friendly natural language when performing interference detection. That is, they only need to provide what they want to do and what goals they want to achieve. The interference detection steps and methods can be automatically generated and implemented, and can be continuously adjusted and optimized based on the evaluation results during the process. Specific application examples are described below:
[0097] During implementation, the user needs to perform interference detection on cells under Site 6, and the detection results are presented as a GIS map. The operation and maintenance user uses the system to input: "Start interference detection for Site 6 at 6:00 AM," and the results are presented as a GIS map. The system uses the intent translation module to identify the elements in the user's intent: {NodeB: 6; Action: Start; Time: April 11, 2023, 6:00 AM; Presentation: GIS}. Based on these four elements and combined with the knowledge graph, the interference detection algorithm processing center module automatically generates a series of detection rules. These include querying NodeB 6's cell performance data, configuration data, and engineering parameter data, performing an initial screening of daily performance data to identify candidate interfering cells under this site, performing a CNN algorithm on the interfering cell performance data, and performing unknown cell segmentation for cells that the convolutional neural network (CNN) algorithm failed to identify. These atomic rules are then pushed to the interference detection processing module for processing. After receiving this atomic rule detection sequence, the processing module executes it sequentially and outputs the final detection results (including GIS data). These results are then pushed to the processing center for transmission to the result output module and the interference detection intent closed-loop module. The interference detection intention closed-loop collects data information for evaluation, provides a visual review of the evaluation results, and adjusts the interference detection knowledge graph.
[0098] During implementation, a user needs to perform interference detection in a fixed area, with the detection results presented as a GIS map. The operation and maintenance user uses the system to input: "Start interference detection for sites in this fixed area at 6:00 AM," and the results are presented in GIS. The system uses the intent translation module to identify the elements in the user's intent: {region: a fixed area; action: start; time: April 11, 2023, 6:00 AM; presentation: GIS}. The system first searches for sites in this fixed area, replacing the region with the four elements. The interference detection algorithm processing center then automatically generates a series of detection rules based on these four elements, combined with knowledge graph entity and entity relationship definitions. For example, it generates a series of atomic rule detection sequences, including querying cell performance data, configuration data, and engineering parameter data for NodeB 6, performing an initial performance data screening to identify candidate interfering cells within this site, applying a CNN algorithm to the interfering cell performance data, and performing unknown cell segmentation for cells not identified by the CNN algorithm. This sequence is then pushed to the interference detection processing module for processing. After acquiring the atomic rule detection sequence, the processing module executes it sequentially and outputs the final detection results (including Geographic Information System (GIS) data). This information is then pushed to the processing center and ultimately transmitted to the result output module and the interference detection intention closed-loop module. The interference detection intention closed-loop collects indicator information for evaluation and provides a visual display of the evaluation results for adjustment of the interference detection knowledge graph.
[0099] In summary, the wireless interference detection method and device provided by the embodiments of the present disclosure implement interference detection using intent-driven and knowledge graph approaches. They mainly include:
[0100] 1. Adopting an intentional approach. During interference detection, users can input the object information to be managed and the specified presentation method. The system will automatically complete the corresponding interference detection and output the results in the specified manner. Users can express interference detection intentions using natural language, including natural language text and voice. This core invention supports various interference detection intention inputs, greatly simplifies input, and improves user usability.
[0101] 2. Automatically generate detection workflows based on the interference detection knowledge graph and intention input. The interference detection algorithm processing center will be based on the interference detection knowledge graph and the information input by intention (such as "interference detection will be carried out on all sites in Shanghai Meile City at 6 o'clock in the morning, and the detection results will be output in GIS", and "interference detection will be carried out on all subnets at 6 o'clock in the morning, and the results will be output in GIS and Table format", etc.), and can automatically generate the detection step workflow of interference detection, send it to the interference detection processing module for processing, and finally output the results as required; the interference detection knowledge graph in this method also provides adjustment and optimization of entities or entity relationships and orchestration functions for further adjustment and expansion of the knowledge graph, improvement of detection methods, and better detection results. This core invention can meet the system's support requirements for interference detection, reduce the difficulty of using the system, enhance the flexibility of adjusting detection methods, and greatly improve network operation efficiency.
[0102] The above description is merely a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will appreciate that various modifications and variations of the present disclosure are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present disclosure should be included within the scope of protection of the present disclosure.
Claims
1. A wireless interference detection method, comprising: Extracting four-tuple information for wireless interference detection according to the wireless interference detection intention and interference intention detection elements input by the user; Determine an atomic rule detection sequence adapted to a pre-constructed wireless interference detection knowledge graph based on the four-tuple information; Wireless interference detection is performed according to the atomic rule detection sequence, and a wireless interference detection result is output.
2. The method according to claim 1, wherein: After extracting the quadruple information for performing wireless interference detection according to the wireless interference detection intention and the interference intention detection element input by the user, the method further includes: Confirming the integrity and legality of the contents of the four-tuple information; Based on the interference intention detection element, interference intention conflict detection is performed on the four-tuple information, and according to a preset conflict resolution strategy, the four-tuple information with a detection result of the interference intention conflict detection as a conflict is adjusted.
3. The method according to claim 2, wherein: The interference intention conflict detection includes at least one of the following: Whether wireless interference detection resources conflict; Whether the wireless interference detection function scenarios conflict; Whether the execution time of the wireless interference detection intent conflicts.
4. The method according to claim 1, wherein: The four-tuple information includes: The object or area information of wireless interference detection, the time information of wireless interference detection, the action information of wireless interference detection, and the presentation method information of wireless interference detection results.
5. The method according to claim 1, wherein: The pre-built wireless interference detection knowledge graph includes at least data entities and entity relationships between the data entities, wherein: The data entity includes at least one of the following: a supported standard for wireless interference detection, a detection rule for wireless interference detection, configuration data of an object for wireless interference detection, an engineering parameter of an object for wireless interference detection, a performance counter or a key performance indicator; The entity relationship includes at least one of the following: a containment relationship, a usage relationship, and a dependency relationship.
6. The method according to claim 1, wherein: Based on the four-tuple information, an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph is determined, including: Determine a rule sequence supported by the wireless interference detection knowledge graph based on the four-tuple information; According to the entity relationship in the rule sequence, obtain a list of atomic rules in the entity rules of the wireless interference detection knowledge graph; The atomic rule list is organized into the atomic rule detection sequence according to a preset strategy order.
7. The method according to claim 1, wherein: Performing wireless interference detection according to the atomic rule detection sequence includes: The atomic rule detection sequence is filled according to the wireless interference detection intention to obtain the interference detection atomic rule Then detect the workflow; The wireless interference detection is performed according to the interference detection atomic rule detection workflow.
8. The method according to claim 1, wherein: After performing wireless interference detection according to the atomic rule detection sequence and outputting the wireless interference detection result, the method further includes: The wireless interference detection results are evaluated, and the entities and entity relationships of the pre-built interference detection knowledge graph are adjusted according to the evaluation results, wherein the adjustment method includes at least one of the following: adding the entities and entity relationships, modifying the entities and entity relationships, and deleting the entities and entity relationships.
9. A wireless interference detection device, comprising: An interference detection intention engine module, configured to extract four-tuple information for wireless interference detection based on wireless interference detection intention and interference intention detection elements input by a user; An interference detection algorithm processing module, configured to determine an atomic rule detection sequence adapted to a pre-built wireless interference detection knowledge graph based on the four-tuple information; The interference detection processing execution module is configured to perform wireless interference detection according to the atomic rule detection sequence and output a wireless interference detection result.
10. The device according to claim 9, wherein: Also includes: The interference detection intention management module is configured to confirm the integrity and legality of the content in the four-tuple information, and perform interference intention conflict detection on the four-tuple information based on the interference intention detection elements, so as to adjust the four-tuple information whose detection result of the interference intention conflict detection is a conflict according to a preset conflict resolution strategy.
11. The device according to claim 9, wherein: Also includes: The interference detection intention closed-loop module is configured to evaluate the wireless interference detection results and adjust the entities and entity relationships of the pre-built interference detection knowledge graph according to the evaluation results, and the adjustment method includes at least one of the following: adding the entities and entity relationships, modifying the entities and entity relationships, and deleting the entities and entity relationships.
12. A computer-readable storage medium having a computer program stored therein, wherein: When the computer program is executed by a processor, the method described in any one of claims 1 to 8 is implemented.
13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 8 when executing the computer program.
Citation Information
Patent Citations
Wireless network connection method and device, terminal equipment and storage medium
CN108337715A
Wireless network scanning method and device, terminal device and storage medium
CN108337718A
Communications system
US20150382364A1
Methods for Detecting Interferers for Handling Interference Mitigation
US20170006501A1
