WO2024055814A1 - Timing signaling generation method and system, electronic device, and storage medium - Google Patents

Timing signaling generation method and system, electronic device, and storage medium Download PDF

Info

Publication number
WO2024055814A1
WO2024055814A1 PCT/CN2023/113864 CN2023113864W WO2024055814A1 WO 2024055814 A1 WO2024055814 A1 WO 2024055814A1 CN 2023113864 W CN2023113864 W CN 2023113864W WO 2024055814 A1 WO2024055814 A1 WO 2024055814A1
Authority
WO
WIPO (PCT)
Prior art keywords
signaling
timing
context
feature information
timing signaling
Prior art date
Application number
PCT/CN2023/113864
Other languages
French (fr)
Chinese (zh)
Inventor
王大海
Original Assignee
中兴通讯股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2024055814A1 publication Critical patent/WO2024055814A1/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/147Network analysis or design for predicting network behaviour
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence

Definitions

  • the present application relates to the field of artificial intelligence technology, and in particular to a timing signaling generation method, system, electronic device and storage medium.
  • the main purpose of this application is to provide a timing signaling generation method, system, electronic device and storage medium, aiming to solve the technical problem of low signaling sequence position accuracy in the prior art.
  • the timing signaling generation method includes:
  • the timing signaling generation system includes:
  • a signaling collection device configured to collect signaling in each network element
  • a feature information collection device configured to collect signaling context feature information corresponding to timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
  • a signaling sorting device configured to sort the signaling collected in each network element, generate corresponding timing signaling, and perform signaling sorting prediction on the timing signaling based on the signaling context characteristics, and adjust the timing The signaling is sequenced to obtain the target timing signaling.
  • the electronic device is a physical device.
  • the electronic device includes: a memory, A processor and a program of the timing signaling generation method stored in the memory and executable on the processor.
  • the program of the timing signaling generation method is executed by the processor, the timing signaling as described above can be realized. Let generate the steps of the method.
  • the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium stores a program for implementing a timing signaling generation method.
  • the program for the timing signaling generation method is executed by a processor, the above-mentioned timing is implemented. Steps of the signaling generation method.
  • Figure 1 is a schematic flow chart of the first embodiment of the timing signaling generation method of the present application.
  • FIG. 2 is a logical view of the timing signaling generation system corresponding to the timing signaling generation method of this application;
  • FIG. 3 is a schematic flow chart of the second embodiment of the timing signaling generation method of the present application.
  • Figure 4 is a schematic flow chart of the third embodiment of the timing signaling generation method of the present application.
  • FIG. 5 is a schematic flowchart of the fourth embodiment of the timing signaling generation method of the present application.
  • Figure 6 is a schematic diagram of the device structure of the hardware operating environment involved in the timing signaling generation method in the embodiment of the present application.
  • an embodiment of the present application provides a timing signaling generation method.
  • the timing signaling generation method includes:
  • Step S10 Sort the signaling collected in each network element and generate corresponding timing signaling
  • Step S20 Collect signaling context feature information corresponding to the timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
  • Step S30 Predict the signaling ordering of the timing signaling based on the signaling context characteristics, adjust the signaling ordering of the timing signaling, and obtain the target timing signaling.
  • steps S10 to S30 include: collecting at least one piece of signaling in each network element, based on each signaling
  • the signaling characteristic value of the signal is correlated, and the initial timing signaling is obtained.
  • the initial timing signaling is initially sorted to obtain the timing signaling.
  • the initial sorting method can be signaling sorting based on time difference. method, or other signaling sorting methods, which are not limited here.
  • the signaling characteristic value can be the MD5 value of the original signaling code stream, or a certain value or several values in the signaling cells.
  • the timing signaling collects the signaling feature information of the timing signaling and the signaling feature information of the context timing signaling of the timing signaling, wherein the signaling feature information at least includes a signaling feature, the signaling
  • the characteristics can be any of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling; obtain the signaling characteristics corresponding to each signaling characteristic in the signaling characteristic information value, splicing each signaling feature value into a feature vector to obtain the signaling context features corresponding to the timing signaling; by inputting the signaling context features into the preset signaling ranking prediction model, the timing signaling is sorted Prediction is performed to obtain a signaling ordering prediction result.
  • the signaling ordering of the timing signaling is adjusted to obtain target timing signaling.
  • the signaling ordering prediction result may be a signaling ordering prediction label.
  • the corresponding signaling ordering adjustment strategy can be queried to adjust the signaling ordering of the timing signaling.
  • the ranking prediction model can be a decision tree model or a deep learning network model, which is not limited here.
  • Step S31 By inputting the signaling context features into a preset signaling ranking prediction model for classification, perform signaling ranking prediction on the timing signaling to obtain a signaling ranking prediction label;
  • Step S32 Adjust the signaling ordering of the timing signaling according to the signaling ordering adjustment strategy corresponding to the signaling ordering prediction tag.
  • steps S31 to S32 include: inputting the signaling context features into a preset signaling ranking prediction model, classifying the upper and lower signaling features to obtain a classification label, and using the classification label as the signaling ranking Prediction tag; use the signaling ranking prediction tag as an index to retrieve the corresponding signaling ranking adjustment strategy, and adjust the signaling ranking of the timing signaling according to the signaling ranking adjustment strategy, wherein the signaling ranking adjustment strategy
  • the sorting position of each signaling in the timing signaling can be determined.
  • the preset signaling ordering prediction model can be maintained and updated.
  • the preset signaling ranking prediction model is a decision tree model
  • the training process of the preset signaling ranking prediction model is as follows:
  • the signaling context feature may be a feature vector, and the signaling context feature at least includes a signaling feature value, where the signaling feature value may be used to identify the timing signaling Any one of the source network element type, destination network element type, direction, communication protocol type, event name and information element; create a root node of the decision tree model, where the root node includes at least one signaling context feature; calculate Each signaling feature value splits the Gini impurity of the root node, selects the signaling feature value with the smallest Gini impurity to split the root node, and calculates the Gini impurity of the split child node using each signaling feature value in the split child node.
  • Impurity determine whether the Gini impurity corresponding to each split child node is not greater than the preset Gini impurity threshold. If so, determine that the decision tree model has been constructed. If not, select the signaling feature value with the smallest Gini impurity. Split child nodes until the Gini impurity of each split child node is less than a preset Gini impurity threshold.
  • the preset Gini impurity threshold can be set to 0 or a value close to 0.
  • the preset signaling ranking prediction model is a deep learning network model
  • the preset signaling ranking prediction model is a deep learning network model.
  • the training process of the test model is as follows:
  • the step of predicting the signaling ordering of the timing signaling through the signaling context characteristics, adjusting the signaling ordering of the timing signaling, and obtaining the target timing signaling it also includes:
  • Step S40 display at least one target timing signaling on the preset display interface
  • Step S50 Receive a signaling adjustment instruction through the preset display interface, and adjust the target timing signaling according to the signaling adjustment instruction.
  • steps S40 to S50 include: at least one timing signaling on the preset display interface, and adjusting the target timing signaling in response to a signaling adjustment instruction input through the preset display interface, wherein,
  • the specific operations of adjusting the target timing signaling in the embodiment of the present application include but are not limited to vertical movement of the timing signaling position, resetting of the timing signaling source, resetting of the destination node, and resetting of the virtual network element.
  • the embodiment of the present application can display the target timing signaling on the interface, and the user can further manually adjust the target timing signaling.
  • the embodiment of the present application automatically adjusts the signaling order of the timing signaling based on the upper and lower characteristics of the signaling. , and can further ensure the accuracy of signaling sorting through manual interaction.
  • recalculating based on the preset signaling sorting prediction model can automatically reorder the timing signaling without adjusting the underlying logic of the sorting algorithm, which improves Sequencing efficiency of timing signaling.
  • the timing signaling generation method in the embodiment of the present application is applied to the timing signaling generation system.
  • Figure 2 is a logical view of the timing signaling generation system in the embodiment of the present application.
  • the timing signaling generation system It includes a network element signaling collection device, a signaling sorting device and an expert intelligent collection device.
  • the network element signaling collection device is used to collect signaling from each network element;
  • the signaling sorting device includes an original sorting module and an AI sorting module.
  • the original sorting module is used to perform original sorting on the signaling of each network element and output timing signaling.
  • the AI sorting module is used to perform signaling context characteristics corresponding to the timing signaling and perform signaling sorting prediction on the timing signaling to adjust The signaling sequence of the timing signaling outputs the target timing signaling;
  • the expert intelligent collection device includes a timing display GUI (preset display interface), a signaling location information collector and a signaling location information memory.
  • the signaling location information collector is used To collect the signaling context feature information corresponding to the timing signaling
  • the signaling location information memory is used to store the signaling context feature information corresponding to the timing signaling
  • the timing display GUI is used to display the target timing signaling.
  • the embodiment of the present application provides a timing signaling generation method, that is, sorting the signaling collected in each network element to generate corresponding timing signaling; collecting the signaling context feature information corresponding to the timing signaling, and based on The signaling context feature information constructs the signaling context feature corresponding to the timing signaling; the signaling context feature is used to configure the signaling context feature.
  • the timing signaling predicts the signaling order, adjusts the signaling order of the timing signaling, and obtains the target timing signaling.
  • the embodiment of the present application further collects the context information of the timing signaling, thereby adjusting the signaling position in the timing signaling according to the context information of the timing signaling, thereby reducing the network element clock synchronization deviation and The influence of network delay and other reasons on the signaling position in timing signaling improves the accuracy of signaling position sorting in timing signaling.
  • the step of collecting signaling context feature information corresponding to the timing signaling includes:
  • Step S21 Determine each first context timing signaling of the timing signaling
  • Step S22 Collect signaling feature information of the timing signaling and signaling feature information of each of the first context timing signaling, where the signaling feature information at least includes the source network element type and destination of the timing signaling.
  • the signaling feature information at least includes the source network element type and destination of the timing signaling.
  • Step S23 Determine signaling context feature information based on each of the signaling feature information.
  • the first context timing signaling may be a first preset number of upper timing signalings to the upper side of the timing signaling, or may be a second preset number of timing signalings to the lower side. number of subsequent timing signalings. For example, assuming that the first preset number is M and the second preset number is N, the first context timing signaling can be the upper M timing signaling and the lower N timing signaling of the timing signaling. Timing signaling, the direction of the timing signaling may be receiving or sending, etc., and the event name of the timing signaling may be a response event or a request event, etc.
  • steps S21 to S23 include: determining a first preset number of upper timing signalings to the upper side and a second preset number of lower timing signalings to the lower side of the timing signaling as Each first context timing signaling; collect signaling feature information of the timing signaling and each first context timing signaling, wherein the signaling feature information at least includes a signaling feature, and the signaling feature may be a source Any one of network element type, destination network element type, direction, communication protocol type, event name and information element; each of the signaling feature information is used as the signaling context feature information.
  • the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
  • timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6.
  • the corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3.
  • the corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell is b6.
  • the corresponding signaling characteristic value of the source network element type of C is c1, the corresponding destination network element type is c2, and the corresponding direction is c3, the corresponding communication protocol type is c4, the corresponding event name is c5 and the corresponding cell is c6, then the final signaling context feature is the feature vector (a1, a2, a3, a4, a5, a6, b1, b2 , b3, b4, b5, b6, c1, c2, c3, c4, c5, c6).
  • the step of determining the signaling context feature information based on each of the signaling feature information includes:
  • Step S231 detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
  • Step S232 if it exists, obtain the vertical movement distance corresponding to the timing signaling of vertical movement
  • Step S233 Use each of the signaling feature information and the vertical movement distance together as signaling context feature information. interest.
  • timing signaling there is usually vertical movement timing signaling in the timing signaling.
  • the context timing signaling of this timing signaling usually also has an impact on the ordering of timing signaling after vertical movement. Therefore, it is necessary to Whether the context timing signaling of the timing signaling moves vertically is one of the factors that determines how to sequence the timing signaling.
  • steps S231 to S233 include: detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, obtaining the timing signaling.
  • the vertical movement distance corresponding to the timing signaling of vertical movement; each of the signaling feature information and the vertical movement distance are jointly used as signaling context feature information.
  • the source network element of the timing signaling On the basis of the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of vertical movement distance of vertical movement timing signaling on signaling sequencing can also be considered to further ensure that the structure The accuracy of the signaling context characteristics of the timing signaling is further improved, thereby further improving the accuracy of signaling sequencing prediction.
  • the step of constructing the signaling context features corresponding to the timing signaling based on the signaling context feature information is as follows:
  • timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6.
  • the corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3.
  • the corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell is b6.
  • the final signaling context feature is a feature vector (a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5, b6, 2, c1, c2, c3, c4, c5, c6).
  • the embodiment of the present application provides a method for determining context characteristic information, that is, determining each first context timing signaling of the timing signaling; collecting the signaling characteristic information of the timing signaling and each of the first context Signaling characteristic information of timing signaling, wherein the signaling characteristic information includes at least one of the source network element type, destination network element type, direction, communication protocol type, event name and information element of timing signaling; according to each The signaling feature information determines the signaling context feature information.
  • the embodiment of this application fully considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and cell of the timing signaling on the signaling order, as well as the context of the timing signaling and the source network of the timing signaling.
  • the step of determining the signaling context feature information based on each of the signaling feature information includes:
  • Step A10 Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
  • Step A20 if it exists, determine each second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node and each second context timing of the timing signaling reset by the endpoint node. Node association relationship information between signaling endpoint nodes;
  • Step A30 Use each of the signaling feature information and the node association relationship information together as signaling context feature information.
  • the endpoint node of the timing signaling when manually adjusting the timing signaling, the endpoint node of the timing signaling is often reset, and whether the reset of the endpoint node is reasonable will also have an impact on the timing signaling.
  • the endpoint node can be a timing signaling source node or destination node.
  • steps A10 to A30 include: detecting whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is timing signaling for endpoint node reset, , then the endpoint node reset timing signaling, the third preset number of the above timing signaling, and the fourth preset number of the following timing signaling, are obtained as each second context timing. signaling, determine the association between the endpoint node of each second context timing signaling and the endpoint node of the timing signaling, and obtain the node association information, wherein the node association information may be an endpoint node characterizing the timing signaling.
  • the node association relationship vector is consistent with the endpoint node of each second context timing signaling; each of the signaling feature information and the node association relationship information are jointly used as the signaling context feature information.
  • timing signaling A has a first context timing signaling B which is the timing signaling reset by the endpoint node.
  • the second context timing signaling of B is respectively E, F and H.
  • the source node and destination node of B are respectively.
  • the node association vector can be ((1,1 ), (1, 0), (0, 0)), where (1, 1) means that the source nodes and destination nodes of B and E are consistent, (1, 0) means that the source nodes of B and F are consistent, but The destination node is inconsistent. (0,0) means that the source node and destination node of B and H are inconsistent.
  • the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
  • Timing context characteristics corresponding to timing signaling For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6.
  • the corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3.
  • the corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell element is b6.
  • B is the timing signaling for endpoint node reset
  • the corresponding node association vector is 111000
  • the source network element type of C corresponds to If the signaling characteristic value is c1, the corresponding destination network element type is c2, the corresponding direction is c3, the corresponding communication protocol type is c4, the corresponding event name is c5, and the corresponding cell is c6, then the final signaling context
  • the features are feature vectors (a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5, b6, 111000, c1, c2, c3, c4, c5, c6).
  • the embodiment of the present application provides a method for determining context feature information, that is, detecting whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if it exists, determine The endpoint node Point each second context timing signaling of the reset timing signaling, and obtain the node association relationship between the endpoint node of the reset timing signaling of the endpoint node and each endpoint node of the second context timing signaling.
  • Information use each of the signaling feature information and the node association information together as signaling context feature information.
  • the embodiment of this application considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling on the signaling order, as well as the context of the timing signaling.
  • the source network element of the timing signaling Based on the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of endpoint node reset timing signaling on signaling sequencing is also considered, making decisions on how to adjust timing
  • the decision-making factors of signaling ordering are more abundant, so the accuracy of the signaling context features of the constructed timing signaling can be further ensured, thereby further improving the accuracy of signaling ordering prediction.
  • the step of determining the signaling context feature information based on each of the signaling feature information includes:
  • Step B10 Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
  • Step B20 If there is timing signaling of vertical movement, obtain the vertical movement distance corresponding to the timing signaling of vertical movement;
  • Step B30 Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
  • Step B40 If there is timing signaling for reset of the endpoint node, determine each second context timing signaling of the timing signaling for reset of the endpoint node, and obtain the endpoint node of the timing signaling for reset of the endpoint node. Node association relationship information with each endpoint node of the second context timing signaling;
  • Step B50 Use each of the signaling feature information, the vertical movement distance and the node association information together as signaling context feature information.
  • steps B10 to B50 include: detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, obtaining the timing signaling.
  • the vertical movement distance corresponding to the timing signaling of vertical movement detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is timing signaling for endpoint node reset, command, the endpoint node resets the timing signaling to the third preset number of the above timing signaling and the fourth preset number of the following timing signaling to the bottom as each second context.
  • Timing signaling determining the association between the endpoint node of each second context timing signaling and the endpoint node of the timing signaling, and obtaining node association information, wherein the node association information can be an endpoint characterizing the timing signaling.
  • a node association vector indicating whether the node is consistent with the endpoint node of each second context timing signaling; each of the signaling feature information, the vertical movement distance and the node association information are collectively used as the signaling context feature information.
  • the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
  • the correlation vectors are spliced into feature vectors to obtain the signaling context features corresponding to the timing signaling. For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5 and the corresponding cell is a6.
  • A is vertical movement timing signaling, the vertical movement distance is 2 lines, and the signaling characteristic value corresponding to the source network element type of B is b1 , the corresponding destination network element type is b2, the corresponding direction is b3, the corresponding communication protocol type is b4, the corresponding event name is b5 and the corresponding cell is b6,
  • B is the timing signaling of endpoint node reset, corresponding
  • the node association vector of is 111000
  • the signaling characteristic value corresponding to the source network element type of C is c1
  • the corresponding destination network element type is c2
  • the corresponding direction is c3
  • the corresponding communication protocol type is c4
  • the corresponding event name is c5 and the corresponding cell is c6
  • the final signaling context feature is the feature vector (a1, a2, a3, a4, a5, a6, 2, b1, b2, b3, b4, b5, b6, 111000, c1 , c2, c3, c
  • Embodiments of the present application provide a method for determining context feature information, that is, detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, command, obtain the vertical movement distance corresponding to the vertical movement timing signaling; detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is an endpoint node Reset timing signaling, then determine each second context timing signaling of the endpoint node's reset timing signaling, and obtain the endpoint node and each of the second contexts of the endpoint node's reset timing signaling.
  • Node association information between endpoint nodes of timing signaling; each of the signaling feature information, the vertical movement distance and the node association information are collectively used as signaling context feature information.
  • the embodiment of this application considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling on the signaling order, as well as the context of the timing signaling.
  • the source network element of the timing signaling On the basis of the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of endpoint node reset timing signaling and vertical movement timing signaling on signaling is also fully considered.
  • the influence of signaling ordering makes the decision-making factors of how to adjust the signaling ordering of timing signaling more abundant, so it can further ensure the accuracy of the signaling context features of the constructed timing signaling, thereby further improving the accuracy of signaling ordering prediction. .
  • the timing signaling generation system includes:
  • the timing signaling generation system includes:
  • Signaling collection device used to collect signaling in each network element
  • a feature information collection device configured to collect signaling context feature information corresponding to timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
  • a signaling sorting device used to sort the signaling collected in each network element, generate corresponding timing signaling, and predict the signaling sorting of the timing signaling through the signaling context characteristics, and adjust the timing The signaling is sequenced to obtain the target timing signaling.
  • the feature information collection device is also used to:
  • signaling feature information of the timing signaling and signaling feature information of each of the first context timing signaling where the signaling feature information at least includes the source network element type and destination network element type of the timing signaling. , direction, communication protocol type, event name and one of the information elements;
  • signaling context feature information is determined.
  • the feature information collection device is also used to:
  • Each of the signaling feature information and the vertical movement distance are collectively used as signaling context feature information.
  • the feature information collection device is also used to:
  • Each of the signaling feature information and the node association relationship information are collectively used as signaling context feature information.
  • the feature information collection device is also used to:
  • timing signaling reset by the endpoint node determine each second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node and each of the timing signaling reset by the endpoint node. node association relationship information between the endpoint nodes of the second context timing signaling;
  • Each of the signaling feature information, the vertical movement distance and the node association relationship information are collectively used as signaling context feature information.
  • the signaling sequencing device is also used to:
  • the signaling ranking prediction is performed on the timing signaling to obtain a signaling ranking prediction label
  • the signaling ordering of the timing signaling is adjusted according to the signaling ordering adjustment strategy corresponding to the signaling ordering prediction tag.
  • the timing signaling generation system is further used for:
  • a signaling adjustment instruction is received through the preset display interface, and the target timing signaling is adjusted according to the signaling adjustment instruction.
  • the timing signaling generation system provided by this application adopts the timing signaling generation method in the above embodiment to solve the technical problem of low accuracy of signaling sorting position.
  • the beneficial effects of the timing signaling generation system provided by the embodiments of the present application are the same as those of the timing signaling generation method provided by the above embodiments, and other technical features in the timing signaling generation system are the same as those of the timing signaling generation method provided by the above embodiments.
  • the features disclosed in the methods of the above embodiments are the same and will not be described again here.
  • the embodiment of the present application provides an electronic device, the electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the timing signaling generation method in the above embodiment 1. Law.
  • Electronic devices in embodiments of the present disclosure may include, but are not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablets), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc.
  • PDAs Personal Digital Assistants
  • PADs Tablets
  • PMPs Portable Multimedia Players
  • vehicle-mounted terminals such as Mobile terminals such as car navigation terminals
  • fixed terminals such as digital TVs, desktop computers, etc.
  • the electronic device shown in FIG. 6 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.
  • the electronic device may include a processing device (such as a central processing unit, a graphics processor, etc.) that may be loaded into a random access memory (RAM) according to a program stored in a read-only memory (ROM) or from a storage device. perform various appropriate actions and processing according to the program in it.
  • RAM random access memory
  • ROM read-only memory
  • various programs and data required for the operation of the electronic device are also stored.
  • the processing device, ROM and RAM are connected to each other via a bus. Input/output (I/O) interfaces are also connected to the bus.
  • the following systems can be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCDs), speakers, vibrators Output devices, etc.; storage devices including tapes, hard disks, etc.; and communication devices.
  • input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.
  • LCDs liquid crystal displays
  • speakers vibrators Output devices
  • storage devices including tapes, hard disks, etc.
  • communication devices may allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data.
  • embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication device, or from a storage device, or from a ROM.
  • the computer program is executed by the processing device, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
  • the electronic device provided by this application adopts the timing signaling generation method in the above embodiment to solve the technical problem of low accuracy of signaling sorting position.
  • the beneficial effects of the electronic device provided by the embodiments of the present application are the same as those of the timing signaling generation method provided by the above-mentioned embodiments, and other technical features in the electronic device are the same as those disclosed by the above-mentioned embodiments. The characteristics are the same and will not be repeated here.
  • This embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon.
  • the computer-readable program instructions are used to execute the method for generating timing signaling in the above-mentioned Embodiment 1.
  • the computer-readable storage medium provided by the embodiment of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof.
  • computer readable storage media More specific examples may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, system, or device. Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.
  • the above-mentioned computer-readable storage medium may be included in the electronic device; it may also exist independently without being assembled into the electronic device.
  • the above computer-readable storage medium carries one or more programs.
  • the electronic device sorts the signaling collected in each network element and generates corresponding timing signaling; Collect signaling context feature information corresponding to the timing signaling, construct signaling context features corresponding to the timing signaling based on the signaling context feature information, and perform processing on the timing signaling using the signaling context features Prediction of signaling ordering adjusts the signaling ordering of the timing signaling to obtain target timing signaling.
  • Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural programming language—such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider through Internet connection
  • each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
  • the modules involved in the embodiments of the present disclosure can be implemented in software or hardware. Among them, the name of the module does not constitute a limitation on the unit itself under certain circumstances.
  • the computer-readable storage medium provided by this application stores computer-readable program instructions for executing the above-mentioned timing signaling generation method, and solves the technical problem of low accuracy of signaling sorting positions.
  • the beneficial effects of the computer-readable storage medium provided by the embodiments of the present application are the same as the beneficial effects of the timing signaling generation method provided by the above-mentioned embodiments, and will not be described again here.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

The present application discloses a timing signaling generation method and system, an electronic device, and a storage medium. The timing signaling generation method comprises: sorting signaling collected in network elements to generate corresponding timing signaling; collecting signaling context feature information corresponding to the timing signaling, and according to the signaling context feature information, constructing signaling context features corresponding to the timing signaling; and performing signaling sorting prediction on the timing signaling by means of the signaling context features, and adjusting the signaling sorting of the timing signaling to obtain target timing signaling.

Description

时序信令生成方法、系统、电子设备及存储介质Timing signaling generation method, system, electronic device and storage medium
相关申请Related applications
本申请要求于2022年9月16号申请的、申请号为202211127071.9的中国专利申请的优先权,其全部内容通过引用结合在本申请中。This application claims priority to the Chinese patent application with application number 202211127071.9 filed on September 16, 2022, the entire content of which is incorporated into this application by reference.
技术领域Technical field
本申请涉及人工智能技术领域,尤其涉及一种时序信令生成方法、系统、电子设备及存储介质。The present application relates to the field of artificial intelligence technology, and in particular to a timing signaling generation method, system, electronic device and storage medium.
背景技术Background technique
为了图形化展示信令,通常需要对网元间的信令进行排序来生成时序信令,目前通常信令的时间差来对信令进行排序,从而生成时序信令,而由于网元时钟同步偏差和网络延迟等原因,常常会导致时序信令中的信令位置不够准确。In order to graphically display signaling, it is usually necessary to sort the signaling between network elements to generate timing signaling. Currently, the signaling is usually sorted according to the time difference of the signaling to generate timing signaling. However, due to the network element clock synchronization deviation Reasons such as network delay and network delay often lead to inaccurate signaling positions in timing signaling.
发明内容Contents of the invention
本申请的主要目的在于提供一种时序信令生成方法、系统、电子设备及存储介质,旨在解决现有技术中信令排序位置准确度低的技术问题。The main purpose of this application is to provide a timing signaling generation method, system, electronic device and storage medium, aiming to solve the technical problem of low signaling sequence position accuracy in the prior art.
为实现上述目的,本申请提供一种时序信令生成方法,所述时序信令生成方法包括:In order to achieve the above purpose, this application provides a timing signaling generation method. The timing signaling generation method includes:
对各网元中采集的信令进行排序,生成对应的时序信令;Sort the signaling collected in each network element and generate corresponding timing signaling;
采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;Collect signaling context feature information corresponding to the timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。Predict the signaling ordering of the timing signaling based on the signaling context characteristics, adjust the signaling ordering of the timing signaling, and obtain target timing signaling.
为实现上述目的,本申请还提供一种时序信令生成系统,所述时序信令生成系统包括:In order to achieve the above purpose, this application also provides a timing signaling generation system. The timing signaling generation system includes:
信令采集装置,设置为采集各网元中的信令;A signaling collection device configured to collect signaling in each network element;
特征信息采集装置,设置为采集时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;A feature information collection device configured to collect signaling context feature information corresponding to timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
信令排序装置,设置为对各网元中采集的信令进行排序,生成对应的时序信令,以及通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。A signaling sorting device configured to sort the signaling collected in each network element, generate corresponding timing signaling, and perform signaling sorting prediction on the timing signaling based on the signaling context characteristics, and adjust the timing The signaling is sequenced to obtain the target timing signaling.
本申请还提供一种电子设备,所述电子设备为实体设备,所述电子设备包括:存储器、 处理器以及存储在所述存储器上并可在所述处理器上运行的所述时序信令生成方法的程序,所述时序信令生成方法的程序被处理器执行时可实现如上述的时序信令生成方法的步骤。This application also provides an electronic device. The electronic device is a physical device. The electronic device includes: a memory, A processor and a program of the timing signaling generation method stored in the memory and executable on the processor. When the program of the timing signaling generation method is executed by the processor, the timing signaling as described above can be realized. Let generate the steps of the method.
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质上存储有实现时序信令生成方法的程序,所述时序信令生成方法的程序被处理器执行时实现如上述的时序信令生成方法的步骤。The present application also provides a computer-readable storage medium. The computer-readable storage medium stores a program for implementing a timing signaling generation method. When the program for the timing signaling generation method is executed by a processor, the above-mentioned timing is implemented. Steps of the signaling generation method.
附图说明Description of drawings
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本申请的实施例,并与说明书一起用于解释本申请的原理。The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,对于本领域普通技术人员而言,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。In order to more clearly explain the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to describe the embodiments or the prior art. Obviously, for those of ordinary skill in the art, It is said that other drawings can be obtained based on these drawings without exerting creative labor.
图1为本申请时序信令生成方法第一实施例的流程示意图;Figure 1 is a schematic flow chart of the first embodiment of the timing signaling generation method of the present application;
图2本申请时序信令生成方法对应的时序信令生成系统的逻辑视图;Figure 2 is a logical view of the timing signaling generation system corresponding to the timing signaling generation method of this application;
图3为本申请时序信令生成方法第二实施例的流程示意图;Figure 3 is a schematic flow chart of the second embodiment of the timing signaling generation method of the present application;
图4为本申请时序信令生成方法第三实施例的流程示意图;Figure 4 is a schematic flow chart of the third embodiment of the timing signaling generation method of the present application;
图5为本申请时序信令生成方法第四实施例的流程示意图;Figure 5 is a schematic flowchart of the fourth embodiment of the timing signaling generation method of the present application;
图6为本申请实施例中时序信令生成方法涉及的硬件运行环境的设备结构示意图。Figure 6 is a schematic diagram of the device structure of the hardware operating environment involved in the timing signaling generation method in the embodiment of the present application.
本申请目的实现、功能特点及优点将结合实施例,参照附图做进一步说明。The realization of the purpose, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings.
具体实施方式Detailed ways
为使本申请的上述目的、特征和优点能够更加明显易懂,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述。显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其它实施例,均属于本申请保护的范围。In order to make the above objects, features and advantages of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without any creative work shall fall within the scope of protection of this application.
参照图1,本申请实施例提供一种时序信令生成方法,在本申请时序信令生成方法的第一实施例中,所述时序信令生成方法包括:Referring to Figure 1, an embodiment of the present application provides a timing signaling generation method. In the first embodiment of the timing signaling generation method of the present application, the timing signaling generation method includes:
步骤S10,对各网元中采集的信令进行排序,生成对应的时序信令;Step S10: Sort the signaling collected in each network element and generate corresponding timing signaling;
步骤S20,采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;Step S20: Collect signaling context feature information corresponding to the timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
步骤S30,通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。Step S30: Predict the signaling ordering of the timing signaling based on the signaling context characteristics, adjust the signaling ordering of the timing signaling, and obtain the target timing signaling.
作为一种示例,步骤S10至步骤S30包括:在各网元中采集至少一条信令,基于各信 令的信令特征值,将各信令进行关联,得到初始时序信令,对所述初始时序信令进行初始排序,得到时序信令,其中,初始排序的方式可以是基于时间差的信令排序方式,也可以为其他信令排序方式,在此不做限定,所述信令特征值可以为信令原始码流的MD5值,也可以为信令信元中的某个值或者某几个值的组合;采集所述时序信令的信令特征信息以及所述时序信令的上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括一信令特征,该信令特征可以为时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的任意一种;获取所述信令特征信息中各信令特征对应的信令特征值,将各信令特征值进行拼接为特征向量,得到时序信令对应的信令上下文特征;通过将所述信令上下文特征输入预设信令排序预测模型,对所述时序信令进行排序预测,得到信令排序预测结果,根据所述排序预测结果,调整所述时序信令的信令排序,得到目标时序信令。其中,所述信令排序预测结果可以为信令排序预测标签,根据该信令排序预测标签可以查询相应的信令排序调整策略,调整所述时序信令的信令排序,所述预设信令排序预测模型可以为决策树模型,也可以深度学习网络模型,在此不做限定。As an example, steps S10 to S30 include: collecting at least one piece of signaling in each network element, based on each signaling The signaling characteristic value of the signal is correlated, and the initial timing signaling is obtained. The initial timing signaling is initially sorted to obtain the timing signaling. The initial sorting method can be signaling sorting based on time difference. method, or other signaling sorting methods, which are not limited here. The signaling characteristic value can be the MD5 value of the original signaling code stream, or a certain value or several values in the signaling cells. a combination of values; collect the signaling feature information of the timing signaling and the signaling feature information of the context timing signaling of the timing signaling, wherein the signaling feature information at least includes a signaling feature, the signaling The characteristics can be any of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling; obtain the signaling characteristics corresponding to each signaling characteristic in the signaling characteristic information value, splicing each signaling feature value into a feature vector to obtain the signaling context features corresponding to the timing signaling; by inputting the signaling context features into the preset signaling ranking prediction model, the timing signaling is sorted Prediction is performed to obtain a signaling ordering prediction result. According to the ordering prediction result, the signaling ordering of the timing signaling is adjusted to obtain target timing signaling. Wherein, the signaling ordering prediction result may be a signaling ordering prediction label. According to the signaling ordering prediction label, the corresponding signaling ordering adjustment strategy can be queried to adjust the signaling ordering of the timing signaling. The ranking prediction model can be a decision tree model or a deep learning network model, which is not limited here.
所述通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,包括:Predicting the signaling ordering of the timing signaling through the signaling context characteristics and adjusting the signaling ordering of the timing signaling include:
步骤S31,通过将所述信令上下文特征输入预设信令排序预测模型中进行分类,对所述时序信令进行信令排序预测,得到信令排序预测标签;Step S31: By inputting the signaling context features into a preset signaling ranking prediction model for classification, perform signaling ranking prediction on the timing signaling to obtain a signaling ranking prediction label;
步骤S32,根据所述信令排序预测标签对应的信令排序调整策略,调整所述时序信令的信令排序。Step S32: Adjust the signaling ordering of the timing signaling according to the signaling ordering adjustment strategy corresponding to the signaling ordering prediction tag.
作为一种示例,步骤S31至步骤S32包括:将所述信令上下文特征输入预设信令排序预测模型,对所述信令上下特征进行分类,得到分类标签,将该分类标签作为信令排序预测标签;以该信令排序预测标签为索引,检索对应的信令排序调整策略,根据该信令排序调整策略,调整所述时序信令的信令排序,其中,所述信令排序调整策略可以决定时序信令中各信令的排序位置。As an example, steps S31 to S32 include: inputting the signaling context features into a preset signaling ranking prediction model, classifying the upper and lower signaling features to obtain a classification label, and using the classification label as the signaling ranking Prediction tag; use the signaling ranking prediction tag as an index to retrieve the corresponding signaling ranking adjustment strategy, and adjust the signaling ranking of the timing signaling according to the signaling ranking adjustment strategy, wherein the signaling ranking adjustment strategy The sorting position of each signaling in the timing signaling can be determined.
作为一种示例,为了保证该预设信令排序预测模型的预测准确度,可以对该预设信令排序预测模型进行维护更新。As an example, in order to ensure the prediction accuracy of the preset signaling ordering prediction model, the preset signaling ordering prediction model can be maintained and updated.
作为一种示例,所述预设信令排序预测模型为决策树模型,该预设信令排序预测模型的训练过程如下:As an example, the preset signaling ranking prediction model is a decision tree model, and the training process of the preset signaling ranking prediction model is as follows:
获取时序信令的信令上下文特征,其中,该信令上下文特征可以为特征向量,该信令上下文特征至少包括一信令特征值,其中,该信令特征值可以用于标识时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的任意一种;创建决策树模型的根节点,其中,该根节点中至少包括一信令上下文特征;计算以各信令特征值分裂所述根节点的基尼不纯度,选取基尼不纯度最小的信令特征值分裂所述根节点;计算以分裂后的子节点中各信令特征值分裂该子节点的基尼不纯度,判断各分裂后的子节点对应的基尼不纯度是否均不大于预设基尼不纯度阈值,若是,则判定决策树模型构建完毕,若否,则选取基尼不纯度最小的信令特征值分裂子节点,直至各分裂后的子节点的基尼不纯度均小于预设基尼不纯度阈值,该预设基尼不纯度阈值可以设置为0或者趋近于0的数值。Obtain the signaling context feature of the timing signaling, where the signaling context feature may be a feature vector, and the signaling context feature at least includes a signaling feature value, where the signaling feature value may be used to identify the timing signaling Any one of the source network element type, destination network element type, direction, communication protocol type, event name and information element; create a root node of the decision tree model, where the root node includes at least one signaling context feature; calculate Each signaling feature value splits the Gini impurity of the root node, selects the signaling feature value with the smallest Gini impurity to split the root node, and calculates the Gini impurity of the split child node using each signaling feature value in the split child node. Impurity, determine whether the Gini impurity corresponding to each split child node is not greater than the preset Gini impurity threshold. If so, determine that the decision tree model has been constructed. If not, select the signaling feature value with the smallest Gini impurity. Split child nodes until the Gini impurity of each split child node is less than a preset Gini impurity threshold. The preset Gini impurity threshold can be set to 0 or a value close to 0.
作为一种示例,所述预设信令排序预测模型为深度学习网络模型,该预设信令排序预 测模型的训练过程如下:As an example, the preset signaling ranking prediction model is a deep learning network model, and the preset signaling ranking prediction model is a deep learning network model. The training process of the test model is as follows:
获取时序信令对应的信令排序真实标签和信令上下文特征,通过将信令上下文特征输入预设信令排序预测模型中进行分类,对时序信令进行信令排序预测,得到信令排序预测标签;计算信令排序真实标签和信令排序预测标签之间的标签相似度损失,若标签相似度损失收敛,则判定预设信令排序预测模型迭代训练更新完毕,若标签相似度损失未收敛,则依据所述标签相似度损失计算的梯度,对预设信令排序预测模型进行更新,并返回执行步骤:获取时序信令对应的信令排序真实标签和信令上下文特征,以进行下一轮迭代。Obtain the real signaling ranking tags and signaling context features corresponding to the timing signaling, and input the signaling context features into the preset signaling ranking prediction model for classification, and perform signaling ranking prediction on the timing signaling to obtain the signaling ranking prediction. tag; calculate the tag similarity loss between the signaling sorting real tag and the signaling sorting predicted tag. If the tag similarity loss converges, it is determined that the iterative training and update of the preset signaling sorting prediction model is completed. If the tag similarity loss does not converge , then update the preset signaling ranking prediction model based on the gradient of the tag similarity loss calculation, and return to the execution step: obtain the signaling ranking real tags and signaling context features corresponding to the timing signaling for the next step. round iteration.
其中,在所述通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令的步骤之后,还包括:Wherein, after the step of predicting the signaling ordering of the timing signaling through the signaling context characteristics, adjusting the signaling ordering of the timing signaling, and obtaining the target timing signaling, it also includes:
步骤S40,在预设显示界面上展示至少一个目标时序信令;Step S40, display at least one target timing signaling on the preset display interface;
步骤S50,通过所述预设显示界面接收信令调整指令,根据所述信令调整指令,对所述目标时序信令进行调整。Step S50: Receive a signaling adjustment instruction through the preset display interface, and adjust the target timing signaling according to the signaling adjustment instruction.
作为一种示例,步骤S40至步骤S50包括:在预设显示界面上至少一条时序信令,响应于通过预设显示界面输入的信令调整指令,对所述目标时序信令进行调整,其中,本申请实施例中对所述目标时序信令进行调整的具体操作包括但不限定于时序信令位置的垂直移动、时序信令源的重新设定、目的节点的重新设定以及虚拟网元的添加等,返回执行步骤:采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征,以对时序信令重新进行排序。As an example, steps S40 to S50 include: at least one timing signaling on the preset display interface, and adjusting the target timing signaling in response to a signaling adjustment instruction input through the preset display interface, wherein, The specific operations of adjusting the target timing signaling in the embodiment of the present application include but are not limited to vertical movement of the timing signaling position, resetting of the timing signaling source, resetting of the destination node, and resetting of the virtual network element. Add, etc., and return to the execution step: collect the signaling context feature information corresponding to the timing signaling, and construct the signaling context feature corresponding to the timing signaling according to the signaling context feature information to re-process the timing signaling. Sort.
本申请实施例可以将目标时序信令在界面进行显示,进而用户可以对目标时序信令进一步进行人工调整,本申请实施例在基于信令上下特征自动调整时序信令的信令排序的基础上,还可以以人工交互的方式进一步保证信令排序的准确度。The embodiment of the present application can display the target timing signaling on the interface, and the user can further manually adjust the target timing signaling. The embodiment of the present application automatically adjusts the signaling order of the timing signaling based on the upper and lower characteristics of the signaling. , and can further ensure the accuracy of signaling sorting through manual interaction.
目前在对时序信令进行调整后,为了重新对时序信令进行排序,通常需要对排序算法的底层逻辑进行调整,效率较低,较为不便。而本申请实施例中在对时序信令进行调整后,基于预设信令排序预测模型重新进行计算,即可自动进行时序信令的重新排序,无需对排序算法的底层逻辑进行调整,提升了时序信令的排序效率。Currently, after adjusting the timing signaling, in order to re-sort the timing signaling, it is usually necessary to adjust the underlying logic of the sorting algorithm, which is inefficient and inconvenient. In the embodiment of the present application, after adjusting the timing signaling, recalculating based on the preset signaling sorting prediction model can automatically reorder the timing signaling without adjusting the underlying logic of the sorting algorithm, which improves Sequencing efficiency of timing signaling.
作为一种示例,本申请实施例中时序信令生成方法应用于时序信令生成系统,参照图2,图2为本申请实施例中时序信令生成系统的逻辑视图,该时序信令生成系统包括网元信令采集装置、信令排序装置和专家智能采集装置,其中,网元信令采集装置用于从各网元中采集信令;信令排序装置包括原始排序模块和AI排序模块,原始排序模块用于对各网元的信令进行原始排序,输出时序信令,AI排序模块用于时序信令对应的信令上下文特征,对所述时序信令进行信令排序预测,以调整所述时序信令的信令排序,输出目标时序信令;专家智能采集装置包括时序展示GUI(预设显示界面)、信令位置信息采集器和信令位置信息存储器,信令位置信息采集器用于采集时序信令对应的信令上下文特征信息,信令位置信息存储器用于存储时序信令对应的信令上下文特征信息,时序展示GUI用于展示目标时序信令。As an example, the timing signaling generation method in the embodiment of the present application is applied to the timing signaling generation system. Refer to Figure 2. Figure 2 is a logical view of the timing signaling generation system in the embodiment of the present application. The timing signaling generation system It includes a network element signaling collection device, a signaling sorting device and an expert intelligent collection device. The network element signaling collection device is used to collect signaling from each network element; the signaling sorting device includes an original sorting module and an AI sorting module. The original sorting module is used to perform original sorting on the signaling of each network element and output timing signaling. The AI sorting module is used to perform signaling context characteristics corresponding to the timing signaling and perform signaling sorting prediction on the timing signaling to adjust The signaling sequence of the timing signaling outputs the target timing signaling; the expert intelligent collection device includes a timing display GUI (preset display interface), a signaling location information collector and a signaling location information memory. The signaling location information collector is used To collect the signaling context feature information corresponding to the timing signaling, the signaling location information memory is used to store the signaling context feature information corresponding to the timing signaling, and the timing display GUI is used to display the target timing signaling.
本申请实施例提供了一种时序信令生成方法,也即对各网元中采集的信令进行排序,生成对应的时序信令;采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;通过所述信令上下文特征对所述 时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。本申请实施例在生成时序信令之后,进一步采集时序信令的上下文信息,从而根据时序信令的上下文信息,对时序信令中的信令位置进行调整,从而可以降低网元时钟同步偏差和网络延迟等原因对时序信令中信令位置的影响,提升时序信令中信令位置排序的准确度。The embodiment of the present application provides a timing signaling generation method, that is, sorting the signaling collected in each network element to generate corresponding timing signaling; collecting the signaling context feature information corresponding to the timing signaling, and based on The signaling context feature information constructs the signaling context feature corresponding to the timing signaling; the signaling context feature is used to configure the signaling context feature. The timing signaling predicts the signaling order, adjusts the signaling order of the timing signaling, and obtains the target timing signaling. After generating the timing signaling, the embodiment of the present application further collects the context information of the timing signaling, thereby adjusting the signaling position in the timing signaling according to the context information of the timing signaling, thereby reducing the network element clock synchronization deviation and The influence of network delay and other reasons on the signaling position in timing signaling improves the accuracy of signaling position sorting in timing signaling.
参照图3,在本申请另一实施例中,与上述实施例相同或相似的内容,可以参考上文介绍,后续不再赘述。所述采集所述时序信令对应的信令上下文特征信息的步骤包括:Referring to Figure 3, in another embodiment of the present application, content that is the same or similar to the above embodiment can be referred to the above introduction and will not be described again. The step of collecting signaling context feature information corresponding to the timing signaling includes:
步骤S21,确定所述时序信令的各第一上下文时序信令;Step S21: Determine each first context timing signaling of the timing signaling;
步骤S22,采集所述时序信令的信令特征信息以及各所述第一上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的一种;Step S22: Collect signaling feature information of the timing signaling and signaling feature information of each of the first context timing signaling, where the signaling feature information at least includes the source network element type and destination of the timing signaling. One of network element type, direction, communication protocol type, event name and information element;
步骤S23,根据各所述信令特征信息,确定信令上下文特征信息。Step S23: Determine signaling context feature information based on each of the signaling feature information.
在本实施例中,所述第一上下文时序信令可以为时序信令往上文的第一预设条数的上文时序信令,也可以为时序信令往下文的第二预设条数的下文时序信令,例如假设第一预设条数为M,第二预设条数为N,则第一上下文时序信令可以为该时序信令的上M条时序信令和下N条时序信令,所述时序信令的方向可以为接收或者发送等,所述时序信令的事件名称可以为应答事件或者请求事件等。In this embodiment, the first context timing signaling may be a first preset number of upper timing signalings to the upper side of the timing signaling, or may be a second preset number of timing signalings to the lower side. number of subsequent timing signalings. For example, assuming that the first preset number is M and the second preset number is N, the first context timing signaling can be the upper M timing signaling and the lower N timing signaling of the timing signaling. Timing signaling, the direction of the timing signaling may be receiving or sending, etc., and the event name of the timing signaling may be a response event or a request event, etc.
作为一种示例,步骤S21至步骤S23包括:确定所述时序信令往上文的第一预设条数的上文时序信令以及往下文的第二预设条数的下文时序信令作为各第一上下文时序信令;采集所述时序信令和各第一上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括一信令特征,该信令特征可以为源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的任意一种;将各所述信令特征信息作为所述信令上下文特征信息。As an example, steps S21 to S23 include: determining a first preset number of upper timing signalings to the upper side and a second preset number of lower timing signalings to the lower side of the timing signaling as Each first context timing signaling; collect signaling feature information of the timing signaling and each first context timing signaling, wherein the signaling feature information at least includes a signaling feature, and the signaling feature may be a source Any one of network element type, destination network element type, direction, communication protocol type, event name and information element; each of the signaling feature information is used as the signaling context feature information.
作为一种示例,所述根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征的步骤包括:As an example, the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
获取所述信令特征信息中各信令特征对应的信令特征值,将各信令特征值拼接为特征向量,得到时序信令对应的信令上下文特征。例如假设时序信令A存在第一上下文时序信令B以及C,假设A的源网元类型对应的信令特征值为a1、对应的目的网元类型为a2、对应的方向为a3、对应的通信协议类型为a4、对应的事件名称为a5以及对应的信元为a6,B的源网元类型对应的信令特征值为b1、对应的目的网元类型为b2、对应的方向为b3、对应的通信协议类型为b4、对应的事件名称为b5以及对应的信元为b6,C的源网元类型对应的信令特征值为c1、对应的目的网元类型为c2、对应的方向为c3、对应的通信协议类型为c4、对应的事件名称为c5以及对应的信元为c6,则最终的信令上下文特征为特征向量(a1,a2,a3,a4,a5,a6,b1,b2,b3,b4,b5,b6,c1,c2,c3,c4,c5,c6)。The signaling feature values corresponding to each signaling feature in the signaling feature information are obtained, and each signaling feature value is spliced into a feature vector to obtain the signaling context features corresponding to the timing signaling. For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6. The corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3. The corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell is b6. The corresponding signaling characteristic value of the source network element type of C is c1, the corresponding destination network element type is c2, and the corresponding direction is c3, the corresponding communication protocol type is c4, the corresponding event name is c5 and the corresponding cell is c6, then the final signaling context feature is the feature vector (a1, a2, a3, a4, a5, a6, b1, b2 , b3, b4, b5, b6, c1, c2, c3, c4, c5, c6).
其中,所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括:Wherein, the step of determining the signaling context feature information based on each of the signaling feature information includes:
步骤S231,检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Step S231, detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
步骤S232,若存在,则获取所述垂直移动的时序信令对应的垂直移动距离;Step S232, if it exists, obtain the vertical movement distance corresponding to the timing signaling of vertical movement;
步骤S233,将各所述信令特征信息和所述垂直移动距离共同作为信令上下文特征信 息。Step S233: Use each of the signaling feature information and the vertical movement distance together as signaling context feature information. interest.
在本实施例中,在时序信令通常还会存在垂直移动的时序信令,该时序信令的上下文时序信令在进行垂直移动后,通常也会对时序信令的排序产生影响,因此需要将该时序信令的上下文时序信令是否垂直移动作为决策时序信令如何排序的因素之一。In this embodiment, there is usually vertical movement timing signaling in the timing signaling. The context timing signaling of this timing signaling usually also has an impact on the ordering of timing signaling after vertical movement. Therefore, it is necessary to Whether the context timing signaling of the timing signaling moves vertically is one of the factors that determines how to sequence the timing signaling.
作为一种示例,步骤S231至步骤S233包括:检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;将各所述信令特征信息和所述垂直移动距离共同作为信令上下文特征信息。本申请实施例在考虑时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响,以及时序信令的上下文时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响的基础上,还考虑垂直移动的时序信令的垂直移动距离对信令排序的影响,可进一步保证构造的时序信令的信令上下文特征的准确度,从而进一步提升信令排序预测的准确度。As an example, steps S231 to S233 include: detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, obtaining the timing signaling. The vertical movement distance corresponding to the timing signaling of vertical movement; each of the signaling feature information and the vertical movement distance are jointly used as signaling context feature information. The embodiment of this application considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling on the signaling order, as well as the context of the timing signaling. The source network element of the timing signaling On the basis of the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of vertical movement distance of vertical movement timing signaling on signaling sequencing can also be considered to further ensure that the structure The accuracy of the signaling context characteristics of the timing signaling is further improved, thereby further improving the accuracy of signaling sequencing prediction.
作为一种示例,所述根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征的步骤如下:As an example, the step of constructing the signaling context features corresponding to the timing signaling based on the signaling context feature information is as follows:
获取所述信令特征信息中各信令特征对应的信令特征值以及垂直移动的时序信令的垂直移动距离,将各信令特征值和垂直移动距离拼接为特征向量,得到时序信令对应的信令上下文特征。例如假设时序信令A存在第一上下文时序信令B以及C,假设A的源网元类型对应的信令特征值为a1、对应的目的网元类型为a2、对应的方向为a3、对应的通信协议类型为a4、对应的事件名称为a5以及对应的信元为a6,B的源网元类型对应的信令特征值为b1、对应的目的网元类型为b2、对应的方向为b3、对应的通信协议类型为b4、对应的事件名称为b5以及对应的信元为b6,B为垂直移动的时序信令,垂直移动距离为2条,C的源网元类型对应的信令特征值为c1、对应的目的网元类型为c2、对应的方向为c3、对应的通信协议类型为c4、对应的事件名称为c5以及对应的信元为c6,则最终的信令上下文特征为特征向量(a1,a2,a3,a4,a5,a6,b1,b2,b3,b4,b5,b6,2,c1,c2,c3,c4,c5,c6)。Obtain the signaling feature value corresponding to each signaling feature in the signaling feature information and the vertical movement distance of the vertically moved timing signaling, and splice each signaling feature value and the vertical movement distance into a feature vector to obtain the timing signaling correspondence Signaling context characteristics. For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6. The corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3. The corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell is b6. B is vertical movement timing signaling, the vertical movement distance is 2 lines, and the signaling characteristic value corresponding to the source network element type of C is c1, the corresponding destination network element type is c2, the corresponding direction is c3, the corresponding communication protocol type is c4, the corresponding event name is c5 and the corresponding cell is c6, then the final signaling context feature is a feature vector (a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5, b6, 2, c1, c2, c3, c4, c5, c6).
本申请实施例提供了一种确定上下文特征信息的方法,也即确定所述时序信令的各第一上下文时序信令;采集所述时序信令的信令特征信息以及各所述第一上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的一种;根据各所述信令特征信息,确定信令上下文特征信息。本申请实施例充分考虑了时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响,以及时序信令的上下文时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响,使得构建的信令上下文特征更未准确,因此基于信令上下文特征对所述时序信令进行信令排序预测,可以提升进行信令排序预测的准确度。The embodiment of the present application provides a method for determining context characteristic information, that is, determining each first context timing signaling of the timing signaling; collecting the signaling characteristic information of the timing signaling and each of the first context Signaling characteristic information of timing signaling, wherein the signaling characteristic information includes at least one of the source network element type, destination network element type, direction, communication protocol type, event name and information element of timing signaling; according to each The signaling feature information determines the signaling context feature information. The embodiment of this application fully considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and cell of the timing signaling on the signaling order, as well as the context of the timing signaling and the source network of the timing signaling. The influence of element type, destination network element type, direction, communication protocol type, event name and cell on signaling ordering makes the constructed signaling context features even more inaccurate. Therefore, the timing signaling is signaled based on the signaling context features. Order ordering prediction can improve the accuracy of signaling ordering prediction.
参照图4,在本申请另一实施例中,与上述实施例相同或相似的内容,可以参考上文介绍,后续不再赘述。所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括: Referring to Figure 4, in another embodiment of the present application, content that is the same or similar to the above embodiment can be referred to the above introduction and will not be described again. The step of determining the signaling context feature information based on each of the signaling feature information includes:
步骤A10,检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;Step A10: Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
步骤A20,若存在,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;Step A20, if it exists, determine each second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node and each second context timing of the timing signaling reset by the endpoint node. Node association relationship information between signaling endpoint nodes;
步骤A30,将各所述信令特征信息和所述节点关联关系信息共同作为信令上下文特征信息。Step A30: Use each of the signaling feature information and the node association relationship information together as signaling context feature information.
在本实施例中,由于在人工调整时序信令时,常常会重设时序信令的端点节点,而端点节点重设是否合理同样会对时序信令产生影响,该端点节点可以为时序信令的源节点或者目的节点。In this embodiment, when manually adjusting the timing signaling, the endpoint node of the timing signaling is often reset, and whether the reset of the endpoint node is reasonable will also have an impact on the timing signaling. The endpoint node can be a timing signaling source node or destination node.
作为一种示例,步骤A10至步骤A30包括:检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;若存在端点节点重设的时序信令,则获取所述端点节点重设的时序信令往上文的第三预设条数的上文时序信令以及往下文的第四预设条数的下文时序信令作为各第二上下文时序信令,确定各第二上下文时序信令的端点节点和时序信令的端点节点之间的关联关系,得到节点关联关系信息,其中,所述节点关联关系信息可以为表征时序信令的端点节点与各第二上下文时序信令的端点节点是否一致的节点关联关系向量;将各所述信令特征信息和所述节点关联关系信息共同作为信令上下文特征信息。例如假设时序信令A存在第一上下文时序信令B为端点节点重设的时序信令,B的各第二上下文时序信令分别为E、F和H,B的源节点和目的节点分别为x和y,E的源节点和目的节点分别为x和y,F的源节点和目的节点分别为x和z,H的端点节点k和m,则节点关联关系向量可以为((1,1),(1,0),(0,0)),其中,(1,1)表示B和E的源节点和目的节点均一致,(1,0)表示B和F的源节点一致,但目的节点不一致,(0,0)表示B和H的源节点和目的节点均不一致。As an example, steps A10 to A30 include: detecting whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is timing signaling for endpoint node reset, , then the endpoint node reset timing signaling, the third preset number of the above timing signaling, and the fourth preset number of the following timing signaling, are obtained as each second context timing. signaling, determine the association between the endpoint node of each second context timing signaling and the endpoint node of the timing signaling, and obtain the node association information, wherein the node association information may be an endpoint node characterizing the timing signaling. The node association relationship vector is consistent with the endpoint node of each second context timing signaling; each of the signaling feature information and the node association relationship information are jointly used as the signaling context feature information. For example, assume that timing signaling A has a first context timing signaling B which is the timing signaling reset by the endpoint node. The second context timing signaling of B is respectively E, F and H. The source node and destination node of B are respectively. x and y, the source node and destination node of E are x and y respectively, the source node and destination node of F are x and z respectively, and the endpoint nodes k and m of H, then the node association vector can be ((1,1 ), (1, 0), (0, 0)), where (1, 1) means that the source nodes and destination nodes of B and E are consistent, (1, 0) means that the source nodes of B and F are consistent, but The destination node is inconsistent. (0,0) means that the source node and destination node of B and H are inconsistent.
作为一种示例,所述根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征的步骤包括:As an example, the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
获取所述信令特征信息中各信令特征对应的信令特征值以及端点节点重设的时序信令的节点关联关系向量,将各信令特征值以及节点关联关系向量拼接为特征向量,得到时序信令对应的信令上下文特征。例如假设时序信令A存在第一上下文时序信令B以及C,假设A的源网元类型对应的信令特征值为a1、对应的目的网元类型为a2、对应的方向为a3、对应的通信协议类型为a4、对应的事件名称为a5以及对应的信元为a6,B的源网元类型对应的信令特征值为b1、对应的目的网元类型为b2、对应的方向为b3、对应的通信协议类型为b4、对应的事件名称为b5以及对应的信元为b6,B为端点节点重设的时序信令,对应的节点关联关系向量为111000,C的源网元类型对应的信令特征值为c1、对应的目的网元类型为c2、对应的方向为c3、对应的通信协议类型为c4、对应的事件名称为c5以及对应的信元为c6,则最终的信令上下文特征为特征向量(a1,a2,a3,a4,a5,a6,b1,b2,b3,b4,b5,b6,111000,c1,c2,c3,c4,c5,c6)。Obtain the signaling feature value corresponding to each signaling feature in the signaling feature information and the node association vector of the timing signaling reset by the endpoint node, and splice each signaling feature value and the node association vector into a feature vector to obtain Signaling context characteristics corresponding to timing signaling. For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5, and the corresponding cell is a6. The corresponding signaling characteristic value of the source network element type of B is b1, the corresponding destination network element type is b2, and the corresponding direction is b3. The corresponding communication protocol type is b4, the corresponding event name is b5, and the corresponding cell element is b6. B is the timing signaling for endpoint node reset, the corresponding node association vector is 111000, and the source network element type of C corresponds to If the signaling characteristic value is c1, the corresponding destination network element type is c2, the corresponding direction is c3, the corresponding communication protocol type is c4, the corresponding event name is c5, and the corresponding cell is c6, then the final signaling context The features are feature vectors (a1, a2, a3, a4, a5, a6, b1, b2, b3, b4, b5, b6, 111000, c1, c2, c3, c4, c5, c6).
本申请实施例提供了一种确定上下文特征信息的方法,也即检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;若存在,则确定所述端点节 点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;将各所述信令特征信息和所述节点关联关系信息共同作为信令上下文特征信息。本申请实施例在考虑时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响,以及时序信令的上下文时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响的基础上,还考虑了端点节点重设的时序信令对信令排序的影响,使得决策如何调整时序信令的信令排序的决策因素更加丰富,因此可进一步保证构造的时序信令的信令上下文特征的准确度,从而进一步提升信令排序预测的准确度。The embodiment of the present application provides a method for determining context feature information, that is, detecting whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if it exists, determine The endpoint node Point each second context timing signaling of the reset timing signaling, and obtain the node association relationship between the endpoint node of the reset timing signaling of the endpoint node and each endpoint node of the second context timing signaling. Information; use each of the signaling feature information and the node association information together as signaling context feature information. The embodiment of this application considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling on the signaling order, as well as the context of the timing signaling. The source network element of the timing signaling Based on the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of endpoint node reset timing signaling on signaling sequencing is also considered, making decisions on how to adjust timing The decision-making factors of signaling ordering are more abundant, so the accuracy of the signaling context features of the constructed timing signaling can be further ensured, thereby further improving the accuracy of signaling ordering prediction.
参照图5,在本申请另一实施例中,与上述实施例相同或相似的内容,可以参考上文介绍,后续不再赘述。所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括:Referring to FIG. 5 , in another embodiment of the present application, content that is the same or similar to the above embodiment can be referred to the above introduction and will not be described again. The step of determining the signaling context feature information based on each of the signaling feature information includes:
步骤B10,检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Step B10: Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
步骤B20,若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;Step B20: If there is timing signaling of vertical movement, obtain the vertical movement distance corresponding to the timing signaling of vertical movement;
步骤B30,检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;Step B30: Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
步骤B40,若存在端点节点重设的时序信令,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;Step B40: If there is timing signaling for reset of the endpoint node, determine each second context timing signaling of the timing signaling for reset of the endpoint node, and obtain the endpoint node of the timing signaling for reset of the endpoint node. Node association relationship information with each endpoint node of the second context timing signaling;
步骤B50,将各所述信令特征信息、所述垂直移动距离和所述节点关联关系信息共同作为信令上下文特征信息。Step B50: Use each of the signaling feature information, the vertical movement distance and the node association information together as signaling context feature information.
作为一种示例,步骤B10至步骤B50包括:检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;若存在端点节点重设的时序信令,则获取所述端点节点重设的时序信令往上文的第三预设条数的上文时序信令以及往下文的第四预设条数的下文时序信令作为各第二上下文时序信令,确定各第二上下文时序信令的端点节点和时序信令的端点节点之间的关联关系,得到节点关联关系信息,其中,所述节点关联关系信息可以为表征时序信令的端点节点与各第二上下文时序信令的端点节点是否一致的节点关联关系向量;将各所述信令特征信息、所述垂直移动距离和所述节点关联关系信息共同作为信令上下文特征信息。As an example, steps B10 to B50 include: detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, obtaining the timing signaling. The vertical movement distance corresponding to the timing signaling of vertical movement; detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is timing signaling for endpoint node reset, command, the endpoint node resets the timing signaling to the third preset number of the above timing signaling and the fourth preset number of the following timing signaling to the bottom as each second context. Timing signaling, determining the association between the endpoint node of each second context timing signaling and the endpoint node of the timing signaling, and obtaining node association information, wherein the node association information can be an endpoint characterizing the timing signaling. A node association vector indicating whether the node is consistent with the endpoint node of each second context timing signaling; each of the signaling feature information, the vertical movement distance and the node association information are collectively used as the signaling context feature information.
作为一种示例,所述根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征的步骤包括:As an example, the step of constructing signaling context features corresponding to the timing signaling based on the signaling context feature information includes:
获取所述信令特征信息中各信令特征对应的信令特征值、垂直移动的时序信令的垂直移动距离以及端点节点重设的时序信令的节点关联关系向量,将各信令特征值以及节点关 联关系向量拼接为特征向量,得到时序信令对应的信令上下文特征。例如假设时序信令A存在第一上下文时序信令B以及C,假设A的源网元类型对应的信令特征值为a1、对应的目的网元类型为a2、对应的方向为a3、对应的通信协议类型为a4、对应的事件名称为a5以及对应的信元为a6,A为垂直移动的时序信令,垂直移动距离为2条,B的源网元类型对应的信令特征值为b1、对应的目的网元类型为b2、对应的方向为b3、对应的通信协议类型为b4、对应的事件名称为b5以及对应的信元为b6,B为端点节点重设的时序信令,对应的节点关联关系向量为111000,C的源网元类型对应的信令特征值为c1、对应的目的网元类型为c2、对应的方向为c3、对应的通信协议类型为c4、对应的事件名称为c5以及对应的信元为c6,则最终的信令上下文特征为特征向量(a1,a2,a3,a4,a5,a6,2,b1,b2,b3,b4,b5,b6,111000,c1,c2,c3,c4,c5,c6)。Obtain the signaling characteristic value corresponding to each signaling characteristic in the signaling characteristic information, the vertical movement distance of the vertical movement timing signaling, and the node association vector of the timing signaling of the endpoint node reset, and combine each signaling characteristic value and node connections The correlation vectors are spliced into feature vectors to obtain the signaling context features corresponding to the timing signaling. For example, assume that timing signaling A has first context timing signaling B and C. It is assumed that the signaling characteristic value corresponding to the source network element type of A is a1, the corresponding destination network element type is a2, the corresponding direction is a3, and the corresponding The communication protocol type is a4, the corresponding event name is a5 and the corresponding cell is a6. A is vertical movement timing signaling, the vertical movement distance is 2 lines, and the signaling characteristic value corresponding to the source network element type of B is b1 , the corresponding destination network element type is b2, the corresponding direction is b3, the corresponding communication protocol type is b4, the corresponding event name is b5 and the corresponding cell is b6, B is the timing signaling of endpoint node reset, corresponding The node association vector of is 111000, the signaling characteristic value corresponding to the source network element type of C is c1, the corresponding destination network element type is c2, the corresponding direction is c3, the corresponding communication protocol type is c4, and the corresponding event name is c5 and the corresponding cell is c6, then the final signaling context feature is the feature vector (a1, a2, a3, a4, a5, a6, 2, b1, b2, b3, b4, b5, b6, 111000, c1 , c2, c3, c4, c5, c6).
本申请实施例提供了一种确定上下文特征信息的方法,也即检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;若存在端点节点重设的时序信令,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;将各所述信令特征信息、所述垂直移动距离和所述节点关联关系信息共同作为信令上下文特征信息。本申请实施例在考虑时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响,以及时序信令的上下文时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元对信令排序的影响的基础上,还充分考虑了端点节点重设的时序信令以及垂直移动的时序信令两者对信令排序的影响,使得决策如何调整时序信令的信令排序的决策因素更加丰富,因此可进一步保证构造的时序信令的信令上下文特征的准确度,从而进一步提升信令排序预测的准确度。Embodiments of the present application provide a method for determining context feature information, that is, detecting whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling; if there is vertical movement timing signaling, command, obtain the vertical movement distance corresponding to the vertical movement timing signaling; detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling; if there is an endpoint node Reset timing signaling, then determine each second context timing signaling of the endpoint node's reset timing signaling, and obtain the endpoint node and each of the second contexts of the endpoint node's reset timing signaling. Node association information between endpoint nodes of timing signaling; each of the signaling feature information, the vertical movement distance and the node association information are collectively used as signaling context feature information. The embodiment of this application considers the impact of the source network element type, destination network element type, direction, communication protocol type, event name and information element of the timing signaling on the signaling order, as well as the context of the timing signaling. The source network element of the timing signaling On the basis of the impact of type, destination network element type, direction, communication protocol type, event name and cell on signaling sequencing, the impact of endpoint node reset timing signaling and vertical movement timing signaling on signaling is also fully considered. The influence of signaling ordering makes the decision-making factors of how to adjust the signaling ordering of timing signaling more abundant, so it can further ensure the accuracy of the signaling context features of the constructed timing signaling, thereby further improving the accuracy of signaling ordering prediction. .
本申请还提供一种时序信令生成系统,所述时序信令生成系统包括:This application also provides a timing signaling generation system. The timing signaling generation system includes:
为实现上述目的,本申请还提供一种时序信令生成系统,所述时序信令生成系统包括:In order to achieve the above purpose, this application also provides a timing signaling generation system. The timing signaling generation system includes:
信令采集装置,用于采集各网元中的信令;Signaling collection device, used to collect signaling in each network element;
特征信息采集装置,用于采集时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;A feature information collection device, configured to collect signaling context feature information corresponding to timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
信令排序装置,用于对各网元中采集的信令进行排序,生成对应的时序信令,以及通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。A signaling sorting device, used to sort the signaling collected in each network element, generate corresponding timing signaling, and predict the signaling sorting of the timing signaling through the signaling context characteristics, and adjust the timing The signaling is sequenced to obtain the target timing signaling.
在一实施方式中,所述特征信息采集装置还用于:In one embodiment, the feature information collection device is also used to:
确定所述时序信令的各第一上下文时序信令;Determine each first context timing signaling of the timing signaling;
采集所述时序信令的信令特征信息以及各所述第一上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的一种;Collect signaling feature information of the timing signaling and signaling feature information of each of the first context timing signaling, where the signaling feature information at least includes the source network element type and destination network element type of the timing signaling. , direction, communication protocol type, event name and one of the information elements;
根据各所述信令特征信息,确定信令上下文特征信息。 Based on each of the signaling feature information, signaling context feature information is determined.
在一实施方式中,所述特征信息采集装置还用于:In one embodiment, the feature information collection device is also used to:
检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
若存在,则获取所述垂直移动的时序信令对应的垂直移动距离;If it exists, obtain the vertical movement distance corresponding to the timing signaling of the vertical movement;
将各所述信令特征信息和所述垂直移动距离共同作为信令上下文特征信息。Each of the signaling feature information and the vertical movement distance are collectively used as signaling context feature information.
在一实施方式中,所述特征信息采集装置还用于:In one embodiment, the feature information collection device is also used to:
检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
若存在,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;If it exists, determine the second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node of the timing signaling reset by the endpoint node and the second context timing signaling of each second context timing signaling. Node association information between endpoint nodes;
将各所述信令特征信息和所述节点关联关系信息共同作为信令上下文特征信息。Each of the signaling feature information and the node association relationship information are collectively used as signaling context feature information.
在一实施方式中,所述特征信息采集装置还用于:In one embodiment, the feature information collection device is also used to:
检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;If there is timing signaling of vertical movement, obtain the vertical movement distance corresponding to the timing signaling of vertical movement;
检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
若存在端点节点重设的时序信令,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;If there is timing signaling reset by the endpoint node, determine each second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node and each of the timing signaling reset by the endpoint node. node association relationship information between the endpoint nodes of the second context timing signaling;
将各所述信令特征信息、所述垂直移动距离和所述节点关联关系信息共同作为信令上下文特征信息。Each of the signaling feature information, the vertical movement distance and the node association relationship information are collectively used as signaling context feature information.
在一实施方式中,所述信令排序装置还用于:In one implementation, the signaling sequencing device is also used to:
通过将所述信令上下文特征输入预设信令排序预测模型中进行分类,对所述时序信令进行信令排序预测,得到信令排序预测标签;By inputting the signaling context features into a preset signaling ranking prediction model for classification, the signaling ranking prediction is performed on the timing signaling to obtain a signaling ranking prediction label;
根据所述信令排序预测标签对应的信令排序调整策略,调整所述时序信令的信令排序。The signaling ordering of the timing signaling is adjusted according to the signaling ordering adjustment strategy corresponding to the signaling ordering prediction tag.
在一实施方式中,所述时序信令生成系统还用于:In one embodiment, the timing signaling generation system is further used for:
在预设显示界面上展示至少一个目标时序信令;Display at least one target timing signaling on the preset display interface;
通过所述预设显示界面接收信令调整指令,根据所述信令调整指令,对所述目标时序信令进行调整。A signaling adjustment instruction is received through the preset display interface, and the target timing signaling is adjusted according to the signaling adjustment instruction.
本申请提供的时序信令生成系统,采用上述实施例中的时序信令生成方法,解决了信令排序位置准确度低的技术问题。与现有技术相比,本申请实施例提供的时序信令生成系统的有益效果与上述实施例提供的时序信令生成方法的有益效果相同,且该时序信令生成系统中的其他技术特征与上述实施例方法公开的特征相同,在此不做赘述。The timing signaling generation system provided by this application adopts the timing signaling generation method in the above embodiment to solve the technical problem of low accuracy of signaling sorting position. Compared with the existing technology, the beneficial effects of the timing signaling generation system provided by the embodiments of the present application are the same as those of the timing signaling generation method provided by the above embodiments, and other technical features in the timing signaling generation system are the same as those of the timing signaling generation method provided by the above embodiments. The features disclosed in the methods of the above embodiments are the same and will not be described again here.
本申请实施例提供一种电子设备,电子设备包括:至少一个处理器;以及,与至少一个处理器通信连接的存储器;其中,存储器存储有可被至少一个处理器执行的指令,指令被至少一个处理器执行,以使至少一个处理器能够执行上述实施例一中的时序信令生成方 法。The embodiment of the present application provides an electronic device, the electronic device comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the timing signaling generation method in the above embodiment 1. Law.
下面参考图6,其示出了适于用来实现本公开实施例的电子设备的结构示意图。本公开实施例中的电子设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例,不应对本公开实施例的功能和使用范围带来任何限制。Referring now to FIG. 6 , a schematic structural diagram of an electronic device suitable for implementing embodiments of the present disclosure is shown. Electronic devices in embodiments of the present disclosure may include, but are not limited to, mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablets), PMPs (Portable Multimedia Players), vehicle-mounted terminals (such as Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 6 is only an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.
如图6所示,电子设备可以包括处理装置(例如中央处理器、图形处理器等),其可以根据存储在只读存储器(ROM)中的程序或者从存储装置加载到随机访问存储器(RAM)中的程序而执行各种适当的动作和处理。在RAM中,还存储有电子设备操作所需的各种程序和数据。处理装置、ROM以及RAM通过总线彼此相连。输入/输出(I/O)接口也连接至总线。As shown in FIG. 6 , the electronic device may include a processing device (such as a central processing unit, a graphics processor, etc.) that may be loaded into a random access memory (RAM) according to a program stored in a read-only memory (ROM) or from a storage device. perform various appropriate actions and processing according to the program in it. In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM and RAM are connected to each other via a bus. Input/output (I/O) interfaces are also connected to the bus.
通常,以下系统可以连接至I/O接口:包括例如触摸屏、触摸板、键盘、鼠标、图像传感器、麦克风、加速度计、陀螺仪等的输入装置;包括例如液晶显示器(LCD)、扬声器、振动器等的输出装置;包括例如磁带、硬盘等的存储装置;以及通信装置。通信装置可以允许电子设备与其他设备进行无线或有线通信以交换数据。虽然图中示出了具有各种系统的电子设备,但是应理解的是,并不要求实施或具备所有示出的系统。可以替代地实施或具备更多或更少的系统。Typically, the following systems can be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; including, for example, liquid crystal displays (LCDs), speakers, vibrators Output devices, etc.; storage devices including tapes, hard disks, etc.; and communication devices. The communication device may allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although the figures illustrate electronic devices having various systems, it is to be understood that implementation or availability of all illustrated systems is not required. More or fewer systems may alternatively be implemented or provided.
在一实施方式中,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信装置从网络上被下载和安装,或者从存储装置被安装,或者从ROM被安装。在该计算机程序被处理装置执行时,执行本公开实施例的方法中限定的上述功能。In one implementation, the processes described above with reference to the flowcharts may be implemented as a computer software program in accordance with embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such embodiments, the computer program may be downloaded and installed from the network through the communication device, or from a storage device, or from a ROM. When the computer program is executed by the processing device, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.
本申请提供的电子设备,采用上述实施例中的时序信令生成方法,解决了信令排序位置准确度低的技术问题。与现有技术相比,本申请实施例提供的电子设备的有益效果与上述实施例提供的时序信令生成方法的有益效果相同,且该电子设备中的其他技术特征与上述实施例方法公开的特征相同,在此不做赘述。The electronic device provided by this application adopts the timing signaling generation method in the above embodiment to solve the technical problem of low accuracy of signaling sorting position. Compared with the existing technology, the beneficial effects of the electronic device provided by the embodiments of the present application are the same as those of the timing signaling generation method provided by the above-mentioned embodiments, and other technical features in the electronic device are the same as those disclosed by the above-mentioned embodiments. The characteristics are the same and will not be repeated here.
应当理解,本公开的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式的描述中,具体特征、结构、材料或者特点可以在任何的一个或多个实施例或示例中以合适的方式结合。It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware, or combinations thereof. In the above description of the embodiments, specific features, structures, materials or characteristics may be combined in any suitable manner in any one or more embodiments or examples.
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。The above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application. should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.
本实施例提供一种计算机可读存储介质,具有存储在其上的计算机可读程序指令,计算机可读程序指令用于执行上述实施例一中的时序信令生成的方法。This embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon. The computer-readable program instructions are used to execute the method for generating timing signaling in the above-mentioned Embodiment 1.
本申请实施例提供的计算机可读存储介质例如可以是U盘,但不限于电、磁、光、电磁、红外线、或半导体的系统、系统或器件,或者任意以上的组合。计算机可读存储介质 的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本实施例中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、系统或者器件使用或者与其结合使用。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。The computer-readable storage medium provided by the embodiment of the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. computer readable storage media More specific examples may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory ( EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this embodiment, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, system, or device. Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.
上述计算机可读存储介质可以是电子设备中所包含的;也可以是单独存在,而未装配入电子设备中。The above-mentioned computer-readable storage medium may be included in the electronic device; it may also exist independently without being assembled into the electronic device.
上述计算机可读存储介质承载有一个或者多个程序,当上述一个或者多个程序被电子设备执行时,使得电子设备:对各网元中采集的信令进行排序,生成对应的时序信令;采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device: sorts the signaling collected in each network element and generates corresponding timing signaling; Collect signaling context feature information corresponding to the timing signaling, construct signaling context features corresponding to the timing signaling based on the signaling context feature information, and perform processing on the timing signaling using the signaling context features Prediction of signaling ordering adjusts the signaling ordering of the timing signaling to obtain target timing signaling.
可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码,上述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional Procedural programming language—such as "C" or a similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In situations involving remote computers, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through Internet connection).
附图中的流程图和框图,图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved. It will also be noted that each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
描述于本公开实施例中所涉及到的模块可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,模块的名称在某种情况下并不构成对该单元本身的限定。The modules involved in the embodiments of the present disclosure can be implemented in software or hardware. Among them, the name of the module does not constitute a limitation on the unit itself under certain circumstances.
本申请提供的计算机可读存储介质,存储有用于执行上述时序信令生成方法的计算机可读程序指令,解决了信令排序位置准确度低的技术问题。与现有技术相比,本申请实施例提供的计算机可读存储介质的有益效果与上述实施例提供的时序信令生成方法的有益效果相同,在此不做赘述。 The computer-readable storage medium provided by this application stores computer-readable program instructions for executing the above-mentioned timing signaling generation method, and solves the technical problem of low accuracy of signaling sorting positions. Compared with the existing technology, the beneficial effects of the computer-readable storage medium provided by the embodiments of the present application are the same as the beneficial effects of the timing signaling generation method provided by the above-mentioned embodiments, and will not be described again here.
以上仅为本申请的可选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利处理范围内。 The above are only optional embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the present application, or directly or indirectly applied to other related technologies fields are all equally included in the patent processing scope of this application.

Claims (10)

  1. 一种时序信令生成方法,其中,所述时序信令生成方法包括:A method for generating timing signaling, wherein the method for generating timing signaling includes:
    对各网元中采集的信令进行排序,生成对应的时序信令;Sort the signaling collected in each network element and generate corresponding timing signaling;
    采集所述时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;Collect signaling context feature information corresponding to the timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
    通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。Predict the signaling ordering of the timing signaling based on the signaling context characteristics, adjust the signaling ordering of the timing signaling, and obtain target timing signaling.
  2. 如权利要求1所述时序信令生成方法,其中,所述采集所述时序信令对应的信令上下文特征信息的步骤包括:The timing signaling generation method according to claim 1, wherein the step of collecting signaling context feature information corresponding to the timing signaling includes:
    确定所述时序信令的各第一上下文时序信令;Determine each first context timing signaling of the timing signaling;
    采集所述时序信令的信令特征信息以及各所述第一上下文时序信令的信令特征信息,其中,所述信令特征信息至少包括时序信令的源网元类型、目的网元类型、方向、通信协议类型、事件名称和信元中的一种;Collect signaling feature information of the timing signaling and signaling feature information of each of the first context timing signaling, where the signaling feature information at least includes the source network element type and destination network element type of the timing signaling. , direction, communication protocol type, event name and one of the information elements;
    根据各所述信令特征信息,确定信令上下文特征信息。Based on each of the signaling feature information, signaling context feature information is determined.
  3. 如权利要求2所述时序信令生成方法,其中,所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括:The timing signaling generation method according to claim 2, wherein the step of determining the signaling context feature information based on each of the signaling feature information includes:
    检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
    若存在,则获取所述垂直移动的时序信令对应的垂直移动距离;If it exists, obtain the vertical movement distance corresponding to the timing signaling of the vertical movement;
    将各所述信令特征信息和所述垂直移动距离共同作为信令上下文特征信息。Each of the signaling feature information and the vertical movement distance are collectively used as signaling context feature information.
  4. 如权利要求2所述时序信令生成方法,其中,所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括:The timing signaling generation method according to claim 2, wherein the step of determining the signaling context feature information based on each of the signaling feature information includes:
    检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令;Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
    若存在,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;If it exists, determine the second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node of the timing signaling reset by the endpoint node and the second context timing signaling of each second context timing signaling. Node association information between endpoint nodes;
    将各所述信令特征信息和所述节点关联关系信息共同作为信令上下文特征信息。Each of the signaling feature information and the node association relationship information are collectively used as signaling context feature information.
  5. 如权利要求2所述时序信令生成方法,其中,所述根据各所述信令特征信息,确定信令上下文特征信息的步骤包括:The timing signaling generation method according to claim 2, wherein the step of determining the signaling context feature information based on each of the signaling feature information includes:
    检测所述时序信令和各所述第一上下文时序信令中是否存在垂直移动的时序信令;Detect whether there is vertical movement timing signaling in the timing signaling and each of the first context timing signaling;
    若存在垂直移动的时序信令,则获取所述垂直移动的时序信令对应的垂直移动距离;If there is timing signaling of vertical movement, obtain the vertical movement distance corresponding to the timing signaling of vertical movement;
    检测所述时序信令和各所述第一上下文时序信令中是否存在端点节点重设的时序信令; Detect whether there is timing signaling for endpoint node reset in the timing signaling and each of the first context timing signaling;
    若存在端点节点重设的时序信令,则确定所述端点节点重设的时序信令的各第二上下文时序信令,并获取所述端点节点重设的时序信令的端点节点与各所述第二上下文时序信令的端点节点之间的节点关联关系信息;If there is timing signaling reset by the endpoint node, determine each second context timing signaling of the timing signaling reset by the endpoint node, and obtain the endpoint node and each of the timing signaling reset by the endpoint node. node association relationship information between the endpoint nodes of the second context timing signaling;
    将各所述信令特征信息、所述垂直移动距离和所述节点关联关系信息共同作为信令上下文特征信息。Each of the signaling feature information, the vertical movement distance and the node association relationship information are collectively used as signaling context feature information.
  6. 如权利要求1所述时序信令生成方法,其中,所述通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,包括:The timing signaling generation method according to claim 1, wherein said predicting the signaling ordering of the timing signaling through the signaling context characteristics and adjusting the signaling ordering of the timing signaling includes:
    通过将所述信令上下文特征输入预设信令排序预测模型中进行分类,对所述时序信令进行信令排序预测,得到信令排序预测标签;By inputting the signaling context features into a preset signaling ranking prediction model for classification, the signaling ranking prediction is performed on the timing signaling to obtain a signaling ranking prediction label;
    根据所述信令排序预测标签对应的信令排序调整策略,调整所述时序信令的信令排序。The signaling ordering of the timing signaling is adjusted according to the signaling ordering adjustment strategy corresponding to the signaling ordering prediction tag.
  7. 如权利要求1所述时序信令生成方法,其中,在所述通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令的步骤之后,还包括:The method for generating timing signaling according to claim 1, wherein the signaling ordering prediction is performed on the timing signaling through the signaling context characteristics, and the signaling ordering of the timing signaling is adjusted to obtain the target timing. After the signaling step, it also includes:
    在预设显示界面上展示至少一个目标时序信令;Display at least one target timing signaling on the preset display interface;
    通过所述预设显示界面接收信令调整指令,根据所述信令调整指令,对所述目标时序信令进行调整。A signaling adjustment instruction is received through the preset display interface, and the target timing signaling is adjusted according to the signaling adjustment instruction.
  8. 一种时序信令生成系统,其中,所述时序信令生成系统包括:A timing signaling generation system, wherein the timing signaling generation system includes:
    信令采集装置,设置为采集各网元中的信令;A signaling collection device configured to collect signaling in each network element;
    特征信息采集装置,设置为采集时序信令对应的信令上下文特征信息,根据所述信令上下文特征信息,构造所述时序信令对应的信令上下文特征;A feature information collection device configured to collect signaling context feature information corresponding to timing signaling, and construct signaling context features corresponding to the timing signaling based on the signaling context feature information;
    信令排序装置,设置为对各网元中采集的信令进行排序,生成对应的时序信令,以及通过所述信令上下文特征对所述时序信令进行信令排序预测,调整所述时序信令的信令排序,得到目标时序信令。A signaling sorting device configured to sort the signaling collected in each network element, generate corresponding timing signaling, and perform signaling sorting prediction on the timing signaling based on the signaling context characteristics, and adjust the timing The signaling is sequenced to obtain the target timing signaling.
  9. 一种电子设备,其中,所述电子设备包括:An electronic device, wherein the electronic device includes:
    至少一个处理器;以及,at least one processor; and,
    与所述至少一个处理器通信连接的存储器;其中,a memory communicatively connected to the at least one processor; wherein,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行权利要求1至7中任一项所述的时序信令生成方法的步骤。The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 7 The steps of the timing signaling generation method.
  10. 一种计算机可读存储介质,其中,所述计算机可读存储介质上存储有实现时序信令生成方法的程序,所述实现时序信令生成方法的程序被处理器执行以实现如权利要求1至7中任一项所述的时序信令生成方法的步骤。 A computer-readable storage medium, wherein a program for implementing a timing signaling generation method is stored on the computer-readable storage medium, and the program for implementing the timing signaling generation method is executed by a processor to implement the steps of claims 1 to 1 The steps of the timing signaling generation method according to any one of 7.
PCT/CN2023/113864 2022-09-16 2023-08-18 Timing signaling generation method and system, electronic device, and storage medium WO2024055814A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211127071.9A CN117768336A (en) 2022-09-16 2022-09-16 Time sequence signaling generation method, system, electronic equipment and storage medium
CN202211127071.9 2022-09-16

Publications (1)

Publication Number Publication Date
WO2024055814A1 true WO2024055814A1 (en) 2024-03-21

Family

ID=90274178

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/113864 WO2024055814A1 (en) 2022-09-16 2023-08-18 Timing signaling generation method and system, electronic device, and storage medium

Country Status (2)

Country Link
CN (1) CN117768336A (en)
WO (1) WO2024055814A1 (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101098204A (en) * 2006-06-29 2008-01-02 华为技术有限公司 Whole network signalling time sequence reverting method
CN106330493A (en) * 2015-06-23 2017-01-11 中兴通讯股份有限公司 Network element signaling sorting method and device, and network management system
CN107347016A (en) * 2016-05-06 2017-11-14 中兴通讯股份有限公司 A kind of signaling process method of model identification and exceptional signaling flow discrimination method
US20190116055A1 (en) * 2017-10-12 2019-04-18 International Business Machines Corporation Device Ranking for Secure Collaboration
CN113568836A (en) * 2021-07-30 2021-10-29 江苏易安联网络技术有限公司 Multi-time-series sample feature extraction method and software detection method applying same

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101098204A (en) * 2006-06-29 2008-01-02 华为技术有限公司 Whole network signalling time sequence reverting method
CN106330493A (en) * 2015-06-23 2017-01-11 中兴通讯股份有限公司 Network element signaling sorting method and device, and network management system
CN107347016A (en) * 2016-05-06 2017-11-14 中兴通讯股份有限公司 A kind of signaling process method of model identification and exceptional signaling flow discrimination method
US20190116055A1 (en) * 2017-10-12 2019-04-18 International Business Machines Corporation Device Ranking for Secure Collaboration
CN113568836A (en) * 2021-07-30 2021-10-29 江苏易安联网络技术有限公司 Multi-time-series sample feature extraction method and software detection method applying same

Also Published As

Publication number Publication date
CN117768336A (en) 2024-03-26

Similar Documents

Publication Publication Date Title
CN114091617B (en) Federal learning modeling optimization method, electronic device, storage medium, and program product
JP2022058915A (en) Method and device for training image recognition model, method and device for recognizing image, electronic device, storage medium, and computer program
CN110222762A (en) Object prediction method, apparatus, equipment and medium
CN110276346A (en) Target area identification model training method, device and computer readable storage medium
JP2023545423A (en) Point cloud segmentation method, device, equipment and storage medium
CN112712795B (en) Labeling data determining method, labeling data determining device, labeling data determining medium and electronic equipment
WO2022171036A1 (en) Video target tracking method, video target tracking apparatus, storage medium, and electronic device
WO2023173878A1 (en) Quantum neural network training method and apparatus
WO2023143016A1 (en) Feature extraction model generation method and apparatus, and image feature extraction method and apparatus
CN113140012B (en) Image processing method, device, medium and electronic equipment
KR20220047228A (en) Method and apparatus for generating image classification model, electronic device, storage medium, computer program, roadside device and cloud control platform
CN115648232B (en) Mechanical arm control method and device, electronic equipment and readable storage medium
CN111738316B (en) Zero sample learning image classification method and device and electronic equipment
US20240046140A1 (en) Simulation method, electronic device, and storage medium
CN115511779B (en) Image detection method, device, electronic equipment and storage medium
EP4332791A1 (en) Blockchain address classification method and apparatus
WO2024055814A1 (en) Timing signaling generation method and system, electronic device, and storage medium
WO2024001653A1 (en) Feature extraction method and apparatus, storage medium, and electronic device
CN112580885A (en) Method, device and equipment for predicting accessory qualification rate and storage medium
CN114647721B (en) Educational intelligent robot control method, device and medium
CN114419327B (en) Image detection method and training method and device of image detection model
CN113255539B (en) Multi-task fusion face positioning method, device, equipment and storage medium
CN112579587B (en) Data cleaning method and device, equipment and storage medium
CN111582456B (en) Method, apparatus, device and medium for generating network model information
CN114237182A (en) Robot scheduling method and system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23864547

Country of ref document: EP

Kind code of ref document: A1