Abnormal information processing method and device, equipment, storage medium and program product

Abstract

The application relates to an abnormal information processing method and device, equipment, a storage medium and a program product. The method comprises the following steps: in the case that an information processing request for an abnormal base station is detected, a target query vector is constructed according to a keyword in the information processing request, an information processing intention is obtained by performing intention analysis on the information processing request, a target information processing mode is determined according to the information processing intention and an information dependency graph, the information dependency graph is constructed based on the dependency relationship between different information processing modes and the containing relationship of each query intention to different information processing modes, a query is performed in an abnormal base station database according to the target query vector, a data query result for the abnormal base station is obtained, and the data query result is processed by using the target information processing mode. The method can improve the efficiency and accuracy of abnormal information processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, and particularly relates to an abnormal information processing method and device, equipment, a storage medium and a program product, which can be applied to the field of wireless communication. BACKGROUND

[0002] With the continuous development of the field of wireless communication, the number of base stations involved in wireless communication also increases. In order to ensure the stability of the operation of the base station, an abnormal information processing mode for performing abnormal analysis on abnormal base stations in communication interruption has appeared.

[0003] In the existing abnormal information processing mode, a query result can be obtained from an abnormal base station database according to a query content input by a user; subsequently, the user can analyze the obtained query result based on the relevant experience of the user, so as to obtain a processing scheme of the abnormal base station.

[0004] However, in the existing mode, on the one hand, the processing mode of the abnormal base station is determined by manually analyzing the query result, which reduces the efficiency of abnormal information processing; on the other hand, when manually analyzing the abnormal base station information in a complex scenario, the accuracy of abnormal information analysis is reduced. SUMMARY

[0005] Therefore, it is necessary to provide an abnormal information processing method, device, equipment, storage medium and program product capable of improving the efficiency and accuracy of abnormal information processing.

[0006] In a first aspect, the present application provides an abnormal information processing method, comprising:

[0007] In a case where an information processing request for an abnormal base station is detected, a target query vector is constructed according to a keyword in the information processing request, and an information processing intention is obtained by performing intention analysis on the information processing request;

[0008] A target information processing mode is determined according to the information processing intention and an information dependency graph; the information dependency graph is constructed based on a dependency relationship between different information processing modes and a containing relationship of each query intention to different information processing modes;

[0009] According to the target query vector, a data query result for the abnormal base station is obtained by querying an abnormal base station database;

[0010] The data query result is processed by using the target information processing mode.

[0011] In one of the embodiments, the target information processing mode is determined according to the information processing intention and the information dependency graph, comprising:

[0012] The information processing mode contained in the information processing intention in the information dependency graph is taken as a first information processing mode; the information processing mode having a dependency relationship with the first information processing mode in the information dependency graph is taken as a second information processing mode; and the target information processing mode is generated according to the first information processing mode, the second information processing mode, and the dependency relationship between the first information processing mode and the second information processing mode.

[0013] In one of the embodiments, according to the target query vector, a query is performed in the abnormal base station database to obtain a data query result for the abnormal base station, including:

[0014] According to the target query vector, a query is performed in the abnormal base station database to obtain an initial query result for the abnormal base station; in a case where the initial query result is empty, the target query vector is split into at least one query restriction vector according to the query restriction conditions contained in the target query vector; each query restriction condition corresponds to one query restriction vector; the at least one query restriction vector is modified to obtain a modified query vector corresponding to the target query vector; according to the modified query vector, a query is performed in the abnormal base station database to obtain a data query result for the abnormal base station.

[0015] In one of the embodiments, the at least one query restriction vector is modified to obtain the modified query vector corresponding to the target query vector, including:

[0016] For each query restriction vector, a query is performed in the abnormal base station database by using the query restriction vector to obtain a sub-query result corresponding to the query restriction vector; the query restriction vector with an empty sub-query result is taken as a to-be-modified restriction vector; the to-be-modified restriction vector is modified to obtain a modified restriction vector; according to the modified restriction vector and the query restriction vector with a non-empty sub-query result, a modified query vector corresponding to the target query vector is determined.

[0017] In one of the embodiments, the to-be-modified restriction vector is modified to obtain the modified restriction vector, including:

[0018] A queryable parameter under an abnormal query restriction condition of the abnormal base station database is determined; the abnormal query restriction condition is the query restriction condition corresponding to the to-be-modified restriction vector; a modified query parameter used to replace an original query parameter in the to-be-modified restriction vector is selected from the queryable parameter; the modified query parameter is used to replace the original query parameter in the to-be-modified restriction vector to obtain the modified restriction vector.

[0019] In one of the embodiments, in a case where there are at least two queryable parameters, the modified query parameter used to replace the original query parameter in the to-be-modified restriction vector is selected from the queryable parameters, including:

[0020] For each queryable parameter, determine a parameter similarity between the original query parameter and the queryable parameter; and replace the original query parameter in the to-be-corrected restriction vector with the queryable parameter to obtain a candidate restriction vector, and use the candidate restriction vector to query the abnormal base station database to obtain a candidate query result corresponding to the queryable parameter; and select a corrected query parameter from the queryable parameters for replacing the original query parameter according to the candidate query result corresponding to each queryable parameter and the parameter similarity.

[0021] In one of the embodiments, selecting a corrected query parameter from the queryable parameters for replacing the original query parameter according to the candidate query result corresponding to each queryable parameter and the parameter similarity includes:

[0022] For each queryable parameter, perform a weighted summation on the candidate query result corresponding to the queryable parameter and the parameter similarity to obtain a selection score corresponding to the queryable parameter; and select a queryable parameter with the largest selection score from the queryable parameters as the corrected query parameter for replacing the original query parameter.

[0023] In a second aspect, the present application further provides an abnormal information processing apparatus, comprising:

[0024] The request processing module is configured to, in the case that an information processing request for an abnormal base station is detected, construct a target query vector according to a keyword in the information processing request, and obtain an information processing intention by performing intention analysis on the information processing request.

[0025] The mode determining module is configured to determine a target information processing mode according to the information processing intention and an information dependency graph; wherein the information dependency graph is constructed based on a dependency relationship between different information processing modes and a containing relationship of each query intention to different information processing modes.

[0026] The result determining module is configured to perform a query in the abnormal base station database according to the target query vector to obtain a data query result for the abnormal base station.

[0027] The result processing module is configured to process the data query result by using the target information processing mode.

[0028] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0029] In the case that an information processing request for an abnormal base station is detected, a target query vector is constructed according to a keyword in the information processing request, and an information processing intention is obtained by performing intention analysis on the information processing request.

[0030] determine the target information processing mode according to the information processing intention and the information dependency graph; wherein the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intention to different information processing modes;

[0031] query in the abnormal base station database according to the target query vector, and obtain a data query result for the abnormal base station;

[0032] process the data query result by using the target information processing mode.

[0033] In the fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0034] In the case that the information processing request for the abnormal base station is detected, a target query vector is constructed according to the keywords in the information processing request, and an information processing intention is obtained by performing intention analysis on the information processing request;

[0035] determine the target information processing mode according to the information processing intention and the information dependency graph; wherein the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intention to different information processing modes;

[0036] query in the abnormal base station database according to the target query vector, and obtain a data query result for the abnormal base station;

[0037] process the data query result by using the target information processing mode.

[0038] In the fifth aspect, the present application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the following steps:

[0039] In the case that the information processing request for the abnormal base station is detected, a target query vector is constructed according to the keywords in the information processing request, and an information processing intention is obtained by performing intention analysis on the information processing request;

[0040] determine the target information processing mode according to the information processing intention and the information dependency graph; wherein the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intention to different information processing modes;

[0041] query in the abnormal base station database according to the target query vector, and obtain a data query result for the abnormal base station;

[0042] process the data query result by using the target information processing mode.

[0043] The abnormal information processing method, device, equipment, storage medium and program product can construct a target query vector according to a keyword in the information processing request, and obtain an information processing intention through intention analysis on the information processing request, so as to determine a target information processing mode according to the information processing intention and an information dependency graph; then, the target query vector is used to query the abnormal base station database to obtain a data query result for the abnormal base station, and the data query result is processed by using the target information processing mode. The method can ensure the adaptability between the information processing mode and the user demand, and improve the flexibility of information processing; the method can directly use the target information processing mode to process the data query result without manual analysis, and can improve the efficiency and accuracy of information processing. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0045] Figure 1 An application environment diagram of an abnormal information processing method in an embodiment;

[0046] Figure 2 A flowchart of an abnormal information processing method in an embodiment;

[0047] Figure 3 A flowchart of determining a target information processing mode in an embodiment;

[0048] Figure 4 An information dependency graph in an embodiment;

[0049] Figure 5 A flowchart of determining a data query result in an embodiment;

[0050] Figure 6 A flowchart of determining a modified query vector in an embodiment;

[0051] Figure 7 A flowchart of determining a modified restriction vector in an embodiment;

[0052] Figure 8 A flowchart of determining a modified restriction vector in another embodiment;

[0053] Figure 9This is a flowchart illustrating an exception information processing method in another embodiment;

[0054] Figure 10 This is a structural block diagram of an exception information processing device in one embodiment;

[0055] Figure 11 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0057] The abnormal information processing method provided in this application embodiment can be applied to, for example, Figure 1 In the application environment shown, base station 102, server 104, and terminal 106 communicate via a network. The abnormal base station database in the data storage system stores abnormal base station information uploaded by abnormal base stations 102. This data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, and tablets. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0058] For example, when server 104 detects an information processing request for an abnormal base station uploaded by terminal 106, it constructs a target query vector based on the keywords in the information processing request and performs intent analysis on the information processing request to obtain the information processing intent. Subsequently, based on the information processing intent and the information dependency graph, it determines the target information processing method and queries the abnormal base station database according to the target query vector to obtain data query results for the abnormal base station. Finally, it processes the data query results using the target information processing method and feeds the information processing results back to terminal 106 for display.

[0059] In one exemplary embodiment, such as Figure 2 As shown, an anomaly information processing method is provided, which can be applied to... Figure 1 Taking the server in the example, the specific steps are as follows:

[0060] S201, upon detecting an information processing request targeting an abnormal base station, construct a target query vector based on the keywords in the information processing request, and perform intent analysis on the information processing request to obtain the information processing intent.

[0061] wherein, the abnormal base station refers to a base station with communication interruption or other problems, i.e., a broken base station; the information processing request refers to a request for processing base station information of the abnormal base station, such as a request for querying the number of abnormal base stations; the target query vector refers to a vector for querying base station information; and the information processing intention refers to an information processing intention contained in the information processing request, such as data retrieval, topology generation, alarm analysis, root cause positioning, and solution.

[0062] In an optional embodiment, when the operation and maintenance personnel of the base station have a demand for information processing, the terminal can display an information query interface to the operation and maintenance personnel. Then, the user can input an information processing field for the abnormal base station in the information query interface and submit it. At this time, the terminal can generate an information processing request based on the information processing field and send the information processing request to the server for processing.

[0063] In another optional embodiment, the server can automatically initiate an information processing request for the abnormal base station at a preset automatic query period. In this embodiment, the initiation method of the information processing request is not limited.

[0064] In an optional embodiment, after detecting the information processing request, the keywords required for querying information can be extracted from the information processing request. Then, the target query vector is constructed using the keywords. For example, a trained large language model can be used to extract the keywords required by a preset query vector template from the information processing request. Then, the extracted keywords are filled into the query vector template to obtain the target query vector.

[0065] For example, the query vector template can be set as {database name: []; table structure metadata information: []; table structure description: []; query task: []}, and if the request involves time query, the item "current time: []" is added. After obtaining the information processing request, the keywords corresponding to the positions of "[]" in the above query vector template can be extracted from the information processing request, and the extracted keywords are filled into the query vector template to obtain a query information table corresponding to the information processing request. Then, the information in the query information table is spliced to obtain the target query vector.

[0066] It can be understood that, in order to ensure the adaptability between the query vector template and the information processing request, a plurality of different types of query vector templates can be preset, and each query vector template can be configured with a corresponding standard processing request. Then, the request similarity between the information processing request and each standard processing request can be calculated, and the query vector template corresponding to the standard processing request with the highest request similarity can be used as the query vector template required by the information processing request.

[0067] In an optional implementation, the information processing request can be subjected to intention analysis processing, so as to obtain an information processing intention of the information processing request.

[0068] For example, the information processing request can be input into an intention recognition model constructed based on a large language model and a deep learning network. The intention recognition model can extract original entities (such as keywords and the like) from the information processing request based on the text generation capability of the large language model. Then, the deep learning network is used to recognize the original entities and determine the probabilities of each candidate entity related to the original entities. Finally, the information processing intention is output in combination with the original entities and the probabilities of each candidate entity. The deep learning network can be constructed based on the following formula (1).

[0069] (1)

[0070] wherein S i is the information processing request; h e (S i ) is the information processing intention; X start is the original entity; X end is the result of the original entity after the deep learning network processing. is a length encoder.

[0071] S202, determining a target information processing mode according to the information processing intention and an information dependency graph.

[0072] The information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intention to different information processing modes. The target information processing mode is the processing mode of the query result.

[0073] It can be understood that, in order to ensure the flexibility of information processing, an information dependency graph can be configured in advance according to the dependency relationship between different data processing modes and the information processing modes contained in each query intention.

[0074] In an optional implementation, the information processing intention can be used to query the dependency relationship between different information processing modes contained in the information dependency graph, so as to obtain different information processing modes required for executing the information processing intention, and the queried information processing modes can be used as the target information processing mode.

[0075] In another optional implementation, a mode determination model can be trained based on the information dependency graph. The information processing intention can be input into the mode determination model, and the mode determination model can output the target information processing mode according to the information processing intention and the model parameters.

[0076] S203, querying the abnormal base station database according to the target query vector to obtain a data query result for the abnormal base station.

[0077] The abnormal base station database is a database for storing base station information of abnormal base stations, which can include real-time databases, vector retrieval libraries, resource information, and different databases; the data query result is a result of querying the abnormal base station database.

[0078] It can be understood that, in order to ensure the efficiency of data query, the base station abnormal information corresponding to the abnormal base station can be preprocessed to obtain an abnormal information vector corresponding to the base station abnormal information; then, the abnormal base station database can be constructed based on the abnormal information vectors of the base station abnormal information.

[0079] For example, a standard information template associated with the query vector template can be preset, and after obtaining the base station abnormal information of the abnormal base station, the metadata of the base station abnormal information can be extracted from the base station abnormal information, and the extracted metadata can be enhanced based on expert knowledge in the relevant field to obtain enhanced metadata; then, the enhanced metadata can be input into the standard information template to obtain the abnormal information vector corresponding to the base station abnormal information. The standard information template can include information such as outage hours, alarm codes, alarm devices, device types, outage areas, and outage times.

[0080] In an optional implementation, for each abnormal information vector in the abnormal base station database, the vector similarity between the abnormal information vector and the target query vector can be determined; then, the data query result for the abnormal base station can be determined according to the vector similarity between the abnormal information vector and the target query vector.

[0081] For example, the vector similarity between the abnormal information vector and the target query vector can be calculated by referring to the following formula (2); then, the abnormal information vector with a vector similarity greater than a similarity threshold can be taken as the data query result of the target query vector.

[0082] (2)

[0083] Wherein, A i is the abnormal information vector; B i is the target query vector; n is the vector length; similarity is the vector similarity between A i and B i .

[0084] S204, processing the data query result by using a target information processing method.

[0085] In an optional implementation, the data query result can be processed by using the target information processing manner to obtain an information processing result corresponding to the information processing request, and then the information processing result is fed back to the operation and maintenance personnel through the information query interface displayed by the terminal for reference by the operation and maintenance personnel in the process of processing the abnormal base station.

[0086] For example, in the case where the target information processing manner is alarm analysis based on the data query result to obtain the generation reason of the abnormal base station, the data query result can be processed by large-area identification and hidden danger analysis to obtain an alarm analysis result, and then the alarm analysis result is used for fault positioning and state analysis to obtain the generation reason of the abnormal base station.

[0087] In the above abnormal information processing method, when the information processing request for the abnormal base station is detected, the target query vector is constructed according to the key words in the information processing request, and the information processing intention is obtained by analyzing the intention of the information processing request, so that the target information processing manner is determined according to the information processing intention and the information dependency graph. Then, the target query vector is used to query the abnormal base station database to obtain the data query result for the abnormal base station, and the data query result is processed by using the target information processing manner. The above method can ensure the adaptability between the information processing manner and the user demand, and improve the flexibility of information processing. In addition, the target information processing manner is directly used to process the data query result without manual analysis, which can improve the efficiency and accuracy of information processing.

[0088] In order to ensure the reliability of the target information processing manner, on the basis of the above embodiments, in this embodiment, an optional way of determining the target information processing manner is provided, as shown in Figure 3 The specific steps include the following steps:

[0089] S301, the information processing manner contained in the information processing intention in the information dependency graph is taken as the first information processing manner.

[0090] The first information processing manner is the information processing manner contained in the information processing intention.

[0091] In an optional implementation, the information processing intention can be used as an index to query the corresponding relationship between the candidate information processing intentions and the candidate information processing manners in the information dependency graph, so as to determine the first information processing manner contained in the information processing intention.

[0092] For example, referring to Figure 4The information dependency graph shown, in the case of the information processing intention being "solution", the first information processing manner is "prevention suggestion" and "solution"; in the case of the information processing intention being "root cause positioning", the first information processing manner is "fault positioning" and "state analysis"; in the case of the information processing intention being "alarm analysis", the first information processing manner is "large-area identification", "hidden danger analysis" and "quality difference identification"; in the case of the information processing intention being "topology generation", the first information processing manner is "work order graph", "link topology" and "associated knowledge"; in the case of the information processing intention being "data retrieval", the first information processing manner is "station break real-time data query", "station break knowledge graph query", "station break vector library retrieval" and "station break resource information".

[0093] S302, in the information dependency graph, the information processing manner dependent on the first information processing manner is taken as the second information processing manner.

[0094] The second information processing manner is the information processing manner dependent on the first information processing manner.

[0095] In an optional embodiment, for each first information processing manner, the first information processing manner can be taken as an index to query the dependency relationship between the candidate information processing manners in the information dependency graph, to obtain a processing manner link containing the first information processing manner; then, each candidate information processing manner before the first information processing manner in the processing manner link is taken as the second information processing manner.

[0096] For example, continuing to refer to Figure 4 The information dependency graph shown, in the case of the first information processing manner being "state analysis" / "fault positioning", "state analysis" depends on "large-area identification", "hidden danger analysis" and "quality difference identification" under "alarm analysis", and "work order graph", "link topology" and "associated knowledge" under "topology generation"; further, "alarm analysis" and "topology generation" depend on "station break real-time data query", "station break knowledge graph query" and "station break resource information", respectively.

[0097] Therefore, the second information processing manner corresponding to "state analysis" / "fault positioning" includes "station break real-time data query", "station break knowledge graph query", "station break resource information", "large-area identification", "hidden danger analysis", "quality difference identification", "work order graph", "link topology" and "associated knowledge".

[0098] S303, according to the first information processing manner, the second information processing manner, and the dependency relationship between the first information processing manner and the second information processing manner, a target information processing manner is generated.

[0099] In an optional implementation, a processing mode link containing the first information processing mode and the second information processing mode can be constructed based on the dependency relationship between the first information processing mode and the second information processing mode, and the processing mode link is taken as the target information processing mode.

[0100] For example, in the case where the information processing request S is "Please help me analyze the out-of-service reasons of the base station with equipment number 950A in region K and give a processing suggestion", it can be determined that the information processing intention of the user is "root cause positioning" and "solution" recommendation.

[0101] With reference to the information dependency graph shown in the foregoing Figure 4 In the case where the information processing intention is "root cause positioning", the target information processing mode is the query result based on "out-of-service real-time data query", and the processing such as "large-area identification", "hidden danger analysis", and "quality difference identification" is performed to obtain an alarm analysis result; the query result based on "out-of-service knowledge graph query" and "out-of-service resource information" is used to perform processing such as "work order graph", "link topology", and "associated knowledge" to obtain a topology generation result; finally, the "root cause positioning" result can be obtained according to the query result of "out-of-service real-time data query", the alarm analysis result, and the topology generation result.

[0102] Similarly, the target information processing mode corresponding to "solution" recommendation is to obtain the "solution" to be recommended according to the "root cause positioning" result and the retrieval result of "out-of-service vector library retrieval".

[0103] In the embodiments of the present application, the first information processing mode and the second information processing mode are determined based on the information dependency graph, and the target information processing mode is generated based on the first information processing mode and the second information processing mode, which can ensure the reliability of the target information processing mode.

[0104] In actual application process, there may be a case that the query result is empty due to information input error, based on this, in order to ensure the accuracy of the data query result, on the basis of the above embodiments, in the present embodiment, an optional way of determining the data query result is provided, as shown in Figure 5 The specific steps include the following steps:

[0105] S501, according to the target query vector, query in the abnormal base station database to obtain the initial query result for the abnormal base station.

[0106] The so-called initial query result is the result of querying based on the target query vector.

[0107] In an optional embodiment, the target query vector can be used to directly query the abnormal base station database to obtain an initial query result for the abnormal base station.

[0108] For example, the vector similarity between each abnormal information vector in the abnormal base station database and the target query vector can be determined respectively; then, the abnormal information vector with a vector similarity greater than a similarity threshold can be taken as the initial query result.

[0109] S502, in the case of an empty initial query result, the target query vector is split into at least one query restriction vector according to the query restriction conditions contained in the target query vector.

[0110] The so-called query restriction condition is a restriction condition when the query vector is used, for example, query time, query area, and abnormal type, etc.; the so-called query restriction vector is the vector information corresponding to the query restriction condition in the target query vector, which can include the query restriction condition and the query parameter. Each query restriction condition corresponds to a query restriction vector.

[0111] In the case of a non-empty initial query result, it is proved that the information processing request is correct, at this time the initial query result can be directly taken as the data query result, and subsequent data processing can be performed.

[0112] In the case of an empty initial query result, in order to ensure the accuracy of the information processing request, the target query vector can be split into query restriction vectors under each query restriction condition based on the query restriction conditions contained in the target query vector.

[0113] For example, in the case where the target query vector H includes time: December 12, 2024, and query area: region F, the target query vector H can be split into query restriction vector H1 "time: December 12, 2024" and query restriction vector H2 "query area: region F".

[0114] S503, at least one query restriction vector is modified to obtain a modified query vector corresponding to the target query vector.

[0115] The so-called modified query vector is a vector obtained by modifying the target query vector.

[0116] In an optional embodiment, for each query restriction vector, the query restriction vector can be input into a trained vector modification model, and the vector modification model can modify the query restriction vector according to the query restriction vector and the model parameter.

[0117] In another alternative implementation, for each query restriction vector, a consistent comparison can be made between the query restriction vector and the standard query vector associated with the query restriction condition corresponding to the query restriction vector. If the query restriction vector exists in the standard query vector, it is proved that the query restriction vector is correct, and no modification is needed for the query restriction vector. If the query restriction vector does not exist in the standard query vector, it is proved that the query restriction vector is abnormal, and the above vector modification model can be used to modify the query restriction vector.

[0118] After the modification of each query restriction vector, the modified query vector corresponding to the target query vector can be obtained.

[0119] S504, according to the modified query vector, querying in the abnormal base station database to obtain the data query result for the abnormal base station.

[0120] In an alternative implementation, after the modified query vector is determined, the modified query vector can be used to re-query in the abnormal base station database to obtain the data query result for the abnormal base station.

[0121] In the embodiments of the present application, by modifying the query restriction vector when the initial query result is empty, and re-querying by using the modified query vector to obtain the data query result, the accuracy of the data query result can be ensured.

[0122] In order to ensure the accuracy of the modified query vector, on the basis of the above embodiments, in the present embodiment, an alternative way of determining the modified query vector is provided, as shown in Figure 6 The specific steps include:

[0123] S601, for each query restriction vector, using the query restriction vector to query in the abnormal base station database to obtain the sub-query result corresponding to the query restriction vector.

[0124] The so-called sub-query result is the query result corresponding to the query restriction vector.

[0125] In an alternative implementation, for each query restriction vector, the query restriction vector can be used to query in the abnormal base station database to obtain the sub-query result corresponding to the query restriction vector.

[0126] S602, the query restriction vector with an empty sub-query result is taken as the to-be-modified restriction vector.

[0127] The so-called to-be-modified restriction vector is the query restriction vector that needs to be modified.

[0128] It can be understood that in the case that the subquery result of a certain query restriction vector is empty, it can be proved that the query restriction vector has a problem, and in this case, the query restriction vector can be taken as a to-be-corrected restriction vector.

[0129] S603, correcting the to-be-corrected restriction vector to obtain a corrected restriction vector.

[0130] The corrected restriction vector is a vector obtained by correcting the to-be-corrected restriction vector.

[0131] In an optional embodiment, for each to-be-corrected restriction vector, the to-be-corrected restriction vector can be input into a trained vector correction model, and the vector correction model corrects the to-be-corrected restriction vector according to the to-be-corrected restriction vector and model parameters to obtain a corrected restriction vector.

[0132] S604, determining a corrected query vector corresponding to the target query vector according to the corrected restriction vector and the query restriction vector whose subquery result is not empty.

[0133] In an optional embodiment, the corrected restriction vector and the query restriction vector whose subquery result is not empty can be arranged based on the order of the query restriction vectors under each query restriction condition in the target query vector, so as to obtain the corrected query vector corresponding to the target query vector.

[0134] In the embodiments of the present application, by taking the query restriction vector whose subquery result is empty as the to-be-corrected restriction vector and correcting the to-be-corrected restriction vector to determine the corrected query vector, the accuracy of the corrected query vector can be ensured.

[0135] In order to ensure the accuracy of the corrected restriction vector, on the basis of the above embodiments, in the present embodiment, an optional way of determining the corrected restriction vector is provided, as shown in Figure 7 The method comprises the following steps:

[0136] S701, determining a queryable parameter of the abnormal base station database under an abnormal query restriction condition.

[0137] The abnormal query restriction condition is a query restriction condition corresponding to the to-be-corrected restriction vector. The queryable parameter is a query parameter that can be queried in the abnormal base station database under the abnormal query restriction condition. For example, if the abnormal base station database only stores abnormal base station data of regions K1, K2 and K3, the queryable parameters include regions K1, K2 and K3 in the case that the abnormal query restriction condition is a query region.

[0138] In an alternative embodiment, the abnormal query restriction condition can be taken as index information to query the abnormal base station database, and obtain the queryable parameters under the abnormal query restriction condition.

[0139] S702, from the queryable parameters, select a correction query parameter to replace the original query parameter in the to-be-corrected restriction vector.

[0140] The original query parameter is the original query parameter in the to-be-corrected restriction vector, and the correction query parameter is the queryable parameter used to replace the original query parameter.

[0141] In an alternative embodiment, for each queryable parameter, the parameter similarity between the queryable parameter and the original query parameter in the to-be-corrected restriction vector can be determined, and then the queryable parameter with the largest parameter similarity in the queryable parameters is taken as the correction query parameter.

[0142] S703, replace the original query parameter in the to-be-corrected restriction vector with the correction query parameter to obtain the corrected restriction vector.

[0143] In an alternative embodiment, the original query parameter contained in the to-be-corrected restriction vector can be replaced with the correction query parameter to obtain the corrected restriction vector.

[0144] In the embodiments of the present application, by selecting the correction query parameter from the queryable parameters and replacing the original query parameter in the to-be-corrected restriction vector with the correction query parameter, the accuracy of the corrected restriction vector can be ensured.

[0145] In order to ensure the accuracy of the corrected restriction vector, on the basis of the above embodiments, in the present embodiment, another alternative way of determining the corrected restriction vector is provided in the case that there are at least two queryable parameters, as shown in the following table: Figure 8 The table specifically includes the following steps:

[0146] S801, for each queryable parameter, determine the parameter similarity between the original query parameter and the queryable parameter.

[0147] The parameter similarity is the similarity between the original query parameter and the queryable parameter.

[0148] In an alternative embodiment, for each queryable parameter, the queryable parameter and the original query parameter can be input into the trained similarity model at the same time, and the similarity model can output the parameter similarity corresponding to the queryable parameter according to the queryable parameter, the original query parameter and the model parameter.

[0149] S802, for each queryable parameter, the queryable parameter is used to replace the original query parameter in the to-be-corrected restriction vector to obtain a candidate restriction vector, and the candidate restriction vector is used to query the abnormal base station database to obtain a candidate query result corresponding to the queryable parameter.

[0150] The candidate restriction vector is a restriction vector after the queryable parameter is replaced, and the candidate query result is a query result obtained after the candidate restriction vector is used for querying.

[0151] In an optional embodiment, for each queryable parameter, the queryable parameter can be used to replace the original query parameter in the to-be-corrected restriction vector to obtain a candidate restriction vector corresponding to the queryable parameter; then, the candidate restriction vector is used to query the abnormal base station database to obtain a candidate query result corresponding to the queryable parameter.

[0152] S803, according to the candidate query result and the parameter similarity corresponding to each queryable parameter, a corrected query parameter used to replace the original query parameter is selected from the queryable parameters.

[0153] In an optional embodiment, the candidate query result and the parameter similarity corresponding to each queryable parameter can be input into a trained parameter selection model at the same time, and the parameter selection model selects a corrected query parameter from the queryable parameters according to the candidate query result and the parameter similarity corresponding to each queryable parameter, and model parameters.

[0154] In another optional embodiment, for each queryable parameter, the candidate query result and the parameter similarity corresponding to the queryable parameter are weighted and summed to obtain a selection score corresponding to the queryable parameter; the queryable parameter with the largest selection score in the queryable parameters is used as the corrected query parameter used to replace the original query parameter. The selection score is a numerical value used to represent the selection probability of the queryable parameter.

[0155] Specifically, the total number of vectors can be calculated according to the number of vectors in the candidate query result corresponding to each queryable parameter; then, for each queryable parameter, the ratio between the number of vectors in the candidate query result corresponding to the queryable parameter and the total number of vectors is used as the query result proportion of the queryable parameter.

[0156] Then, the query result proportion and the parameter similarity corresponding to the queryable parameter can be weighted and summed by using a preset weight coefficient according to formula (3) to obtain a selection score corresponding to the queryable parameter. Further, the queryable parameter with the largest score in the queryable parameters can be directly used as the corrected query parameter used to replace the original query parameter.

[0157] (3)

[0158] Among them, Score N A selection score for the queryable parameter N; P N R represents the percentage of query results corresponding to the queryable parameter N; N The parameter similarity is the parameter similarity corresponding to the queryable parameter N; These are the coefficients used to weight the number of vectors; These are the coefficients used to weight the parameter similarity.

[0159] For example, in a query with the exception condition of a query region, the original query parameter being "region K", and the available query parameters being "region K1", "region K2", and "region K3", the parameter similarity between "region K" and "region K1", "region K2", and "region K3" can be calculated respectively. The parameter similarity between "region K" and "region K1" can be obtained as R. K1 =0.97; the parameter similarity between "Region K" and "Region K2" is R. K2 =0.5; the parameter similarity between "Region K" and "Region K3" is R. K3 =0.1.

[0160] Furthermore, querying the abnormal base station database using "query region: region K1" yields 25 vectors in the candidate query results; querying using "query region: region K2" yields 20 vectors in the candidate query results; and querying using "query region: region K3" yields 5 vectors in the candidate query results. At this point, P can be obtained. K1 =0.5; P K2 =0.4; P K3 =0.1.

[0161] exist Take 0.2, With a value of 0.8, the Score can be calculated. K1 =0.876, Score K2 =0.48, Score K3 =0.1. At this point, we can determine that the corrected query parameter corresponding to “Region K” is “Region K1”. That is, by replacing “Region K” in the target query vector with “Region K1”, we can obtain the corrected query vector.

[0162] In this embodiment of the application, by selecting a corrected query parameter to replace the original query parameter from each query parameter based on the candidate query results and parameter similarity corresponding to each query parameter, the accuracy of the corrected query parameter can be guaranteed.

[0163] Figure 9 For another embodiment of the flowchart of the abnormal information processing method, on the basis of the above embodiment, the present embodiment provides an optional example of the abnormal information processing method. In combination with Figure 9 , the specific implementation process is as follows:

[0164] S901, in the case of detecting an information processing request for an abnormal base station, constructing a target query vector according to the keywords in the information processing request, and obtaining an information processing intention by analyzing the intention of the information processing request.

[0165] S902, in the information dependency graph, the information processing mode contained in the information processing intention is taken as the first information processing mode.

[0166] Among them, the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intention to different information processing modes.

[0167] S903, in the information dependency graph, the information processing mode which has a dependency relationship with the first information processing mode is taken as the second information processing mode.

[0168] S904, according to the first information processing mode, the second information processing mode, and the dependency relationship between the first information processing mode and the second information processing mode, the target information processing mode is generated.

[0169] S905, according to the target query vector, query in the abnormal base station database to obtain the initial query result for the abnormal base station.

[0170] S906, judge whether the initial query result is empty, if yes, execute S907; if not, execute S915.

[0171] S907, according to the query restriction condition contained in the target query vector, the target query vector is split into at least one query restriction vector.

[0172] Among them, each query restriction condition corresponds to a query restriction vector.

[0173] S908, for each query restriction vector, the query restriction vector is used to query in the abnormal base station database to obtain the subquery result corresponding to the query restriction vector.

[0174] S909, the query restriction vector whose subquery result is empty is taken as the to-be-corrected restriction vector, and the queryable parameters of the abnormal base station database under the abnormal restriction condition contained in the to-be-corrected restriction vector are determined.

[0175] S910, for each queryable parameter, determining a parameter similarity between the original query parameter and the queryable parameter; and replacing the original query parameter in the to-be-corrected restriction vector with the queryable parameter to obtain a candidate restriction vector, and performing a query in the abnormal base station database by using the candidate restriction vector to obtain a candidate query result corresponding to the queryable parameter.

[0176] S911, selecting a corrected query parameter for replacing the original query parameter from the queryable parameters according to the candidate query result corresponding to each queryable parameter and the parameter similarity.

[0177] Optionally, for each queryable parameter, performing a weighted summation on the candidate query result corresponding to the queryable parameter and the parameter similarity to obtain a selection score corresponding to the queryable parameter; and selecting, as the corrected query parameter for replacing the original query parameter, the queryable parameter with the largest selection score among the queryable parameters.

[0178] S912, replacing the original query parameter in the to-be-corrected restriction vector with the corrected query parameter to obtain a corrected restriction vector.

[0179] S913, determining a corrected query vector corresponding to the target query vector according to the corrected restriction vector and the query restriction vector with a non-empty sub-query result.

[0180] S914, performing a query in the abnormal base station database according to the corrected query vector to obtain a data query result for the abnormal base station.

[0181] S915, taking the initial query result as the data query result.

[0182] S916, processing the data query result by using the target information processing mode.

[0183] The specific process of S901-S916 can be referred to the description of the method embodiments, and the implementation principle and technical effects are similar, which will not be described here.

[0184] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with other steps or steps or stages in other steps.

[0185] Based on the same inventive concept, the embodiments of the present application also provide an exception information processing apparatus for implementing the above-mentioned exception information processing method. The apparatus provides a solution to the problem similar to the implementation solution described in the above-mentioned method, and therefore the specific limitations in one or more exception information processing apparatus embodiments provided below can refer to the limitations of the exception information processing method described above, which will not be repeated here.

[0186] In an exemplary embodiment, as shown in Figure 10 An exception information processing apparatus 1 is provided, comprising a request processing module 10, a mode determination module 20, a result determination module 30 and a result processing module 40, wherein:

[0187] The request processing module 10 is configured to, in the case of detecting an information processing request for an abnormal base station, construct a target query vector according to a keyword in the information processing request, and perform intent analysis on the information processing request to obtain an information processing intent;

[0188] The mode determination module 20 is configured to determine a target information processing mode according to the information processing intent and an information dependency graph, wherein the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intent to different information processing modes;

[0189] The result determination module 30 is configured to query in an abnormal base station database according to the target query vector to obtain a data query result for the abnormal base station;

[0190] The result processing module 40 is configured to process the data query result using the target information processing mode.

[0191] In an exemplary embodiment, the mode determination module 20 is specifically configured to:

[0192] include the information processing mode contained in the information processing intent in the information dependency graph as a first information processing mode, include the information processing mode in the information dependency graph that has a dependency relationship with the first information processing mode as a second information processing mode, and generate the target information processing mode according to the first information processing mode, the second information processing mode, and the dependency relationship between the first information processing mode and the second information processing mode.

[0193] In an exemplary embodiment, the result determination module 30 comprises:

[0194] A first query unit is configured to query in an abnormal base station database according to the target query vector to obtain an initial query result for the abnormal base station;

[0195] a vector splitting unit, configured to split the target query vector into at least one query restriction vector according to query restriction conditions contained in the target query vector, in a case that the initial query result is empty; wherein each query restriction condition corresponds to one query restriction vector;

[0196] a vector modifying unit, configured to modify the at least one query restriction vector to obtain a modified query vector corresponding to the target query vector;

[0197] a second query unit, configured to query in the abnormal base station database according to the modified query vector to obtain a data query result for the abnormal base station.

[0198] In an exemplary embodiment, the vector modifying unit comprises:

[0199] a first sub-unit, configured to query in the abnormal base station database according to each query restriction vector to obtain a sub-query result corresponding to the query restriction vector;

[0200] a second sub-unit, configured to take a query restriction vector with an empty sub-query result as a to-be-modified restriction vector;

[0201] a third sub-unit, configured to modify the to-be-modified restriction vector to obtain a modified restriction vector;

[0202] a fourth sub-unit, configured to determine the modified query vector corresponding to the target query vector according to the modified restriction vector and the query restriction vector with a non-empty sub-query result.

[0203] In an exemplary embodiment, the third sub-unit is specifically configured to:

[0204] determine a queryable parameter of the abnormal base station database under an abnormal query restriction condition; wherein the abnormal query restriction condition is a query restriction condition corresponding to the to-be-modified restriction vector; select a modified query parameter for replacing an original query parameter in the to-be-modified restriction vector from the queryable parameter; and replace the original query parameter in the to-be-modified restriction vector with the modified query parameter to obtain the modified restriction vector.

[0205] In an exemplary embodiment, in a case that there are at least two queryable parameters, the third sub-unit is further configured to:

[0206] For each queryable parameter, determine a parameter similarity between the original query parameter and the queryable parameter; and replace the original query parameter in the to-be-corrected restriction vector with the queryable parameter to obtain a candidate restriction vector, and use the candidate restriction vector to query the abnormal base station database to obtain a candidate query result corresponding to the queryable parameter; and select a corrected query parameter for replacing the original query parameter from the queryable parameters according to the candidate query result corresponding to each queryable parameter and the parameter similarity.

[0207] In an exemplary embodiment, the third subunit is further configured to:

[0208] For each queryable parameter, perform a weighted sum on the candidate query result corresponding to the queryable parameter and the parameter similarity to obtain a selection score corresponding to the queryable parameter; and select a queryable parameter with the largest selection score from the queryable parameters as the corrected query parameter for replacing the original query parameter.

[0209] The modules in the abnormal information processing apparatus described above can be implemented in whole or in part by software, hardware, and combinations thereof. The modules described above can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the modules.

[0210] In an exemplary embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 11 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store abnormal base station data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with terminals outside through a network connection. The computer program is executed by the processor to implement an abnormal information processing method.

[0211] Those skilled in the art can understand that, Figure 11The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0212] In an embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0213] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0214] In an embodiment, a computer program product is provided, including a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0215] It should be noted that the data (including but not limited to abnormal base station data, etc.) involved in the present application are all data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data need to comply with the relevant provisions.

[0216] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0217] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0218] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. An abnormal information processing method characterized by comprising: The method comprises: In the case of detecting an information processing request for an abnormal base station, constructing a target query vector according to a keyword in the information processing request, and performing intent analysis on the information processing request to obtain an information processing intent; According to the information processing intent and an information dependency graph, determining a target information processing mode; wherein the information dependency graph is constructed based on the dependency relationship between different information processing modes and the inclusion relationship of each query intent to different information processing modes; According to the target query vector, querying in an abnormal base station database to obtain a data query result for the abnormal base station; Processing the data query result by using the target information processing mode.

2. The method of claim 1, wherein, According to the information processing intent and the information dependency graph, determining a target information processing mode, comprising: Taking the information processing mode contained in the information processing intent in the information dependency graph as a first information processing mode; Taking the information processing mode in the information dependency graph which has a dependency relationship with the first information processing mode as a second information processing mode; According to the first information processing mode, the second information processing mode, and the dependency relationship between the first information processing mode and the second information processing mode, generating a target information processing mode.

3. The method of claim 1, wherein, According to the target query vector, querying in an abnormal base station database to obtain a data query result for the abnormal base station, comprising: According to the target query vector, querying in an abnormal base station database to obtain an initial query result for the abnormal base station; In the case that the initial query result is empty, splitting the target query vector into at least one query restriction vector according to the query restriction conditions contained in the target query vector; wherein each query restriction condition corresponds to one query restriction vector; Modifying the at least one query restriction vector to obtain a modified query vector corresponding to the target query vector; According to the modified query vector, querying in the abnormal base station database to obtain a data query result for the abnormal base station.

4. The method of claim 3, wherein, The modification of the at least one query restriction vector to obtain a modified query vector corresponding to the target query vector, comprising: For each query restriction vector, querying in the abnormal base station database by using the query restriction vector to obtain a sub-query result corresponding to the query restriction vector; Taking the query restriction vector with an empty sub-query result as a to-be-modified restriction vector; Modifying the to-be-modified restriction vector to obtain a modified restriction vector; According to the modified restriction vector and the query restriction vector with a non-empty sub-query result, determining a modified query vector corresponding to the target query vector.

5. The method of claim 4, wherein, The modification of the to-be-modified restriction vector to obtain a modified restriction vector, comprising: Determining the queryable parameters of the abnormal base station database under abnormal query restriction conditions; wherein the abnormal query restriction condition is the query restriction condition corresponding to the to-be-modified restriction vector; From the queryable parameters, selecting a modified query parameter for replacing the original query parameter in the to-be-modified restriction vector; The original query parameter in the to-be-modified restriction vector is replaced by the modified query parameter to obtain a modified restriction vector.

6. The method of claim 5, wherein, In the presence of at least two queryable parameters, the modified query parameter used to replace the original query parameter in the to-be-modified restriction vector is selected from the queryable parameters, comprising: For each queryable parameter, determine the parameter similarity between the original query parameter and the queryable parameter; and, The original query parameter in the to-be-modified restriction vector is replaced by the queryable parameter to obtain a candidate restriction vector, and the candidate restriction vector is used to query the abnormal base station database to obtain a candidate query result corresponding to the queryable parameter; According to the candidate query result and the parameter similarity corresponding to each queryable parameter, a modified query parameter used to replace the original query parameter is selected from the queryable parameters.

7. The method of claim 6, wherein, According to the candidate query result and the parameter similarity corresponding to each queryable parameter, a modified query parameter used to replace the original query parameter is selected from the queryable parameters. For each queryable parameter, the candidate query result and the parameter similarity corresponding to the queryable parameter are weighted and summed to obtain a selection score corresponding to the queryable parameter; The queryable parameter with the largest selection score is selected as the modified query parameter used to replace the original query parameter.

8. An abnormality information processing apparatus characterized by comprising: The device comprises: The request processing module is configured to, in a case where an information processing request for an abnormal base station is detected, construct a target query vector according to a keyword in the information processing request, and perform intent analysis on the information processing request to obtain an information processing intent; The mode determination module is configured to determine a target information processing mode according to the information processing intent and an information dependency graph, wherein the information dependency graph is constructed based on a dependency relationship between different information processing modes and a containing relationship of each query intent to different information processing modes; The result determination module is configured to query an abnormal base station database according to the target query vector to obtain a data query result for the abnormal base station; The result processing module is configured to process the data query result using the target information processing mode. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 7.

11. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 7.

Images