A network event processing method and device for tracking points

Abstract

The present invention relates to tracking technology, and specifically to a network event processing method and device for tracking tracking. The tracking trend of tracking access events is processed based on the data of tracking access records in the actual communication network process in the data table. Compared with the tracking event trend elements of the tracking access device in operation, it can more accurately reflect the tracking event trend elements in harsh actual places, and has a stronger guiding significance for actual product development. This method does not need to carry out durability tests on tracking access devices, but processes and handles the access event trend based on the actual communication network data of the access records in the data table, which greatly saves the test cycle and labor costs. This method can realize the tracking trend processing and processing of the corresponding access events of the tracking access device in the preset visited interval, and can be continuously updated as the access frequency of the access record increases, and is easy to operate and highly flexible.

Description

Technical Field

[0001] The present invention relates to network communication technology, and in particular to a network event processing method and device for point tracking. Background Art

[0002] At present, after the terminal is released and used, the tracking points are relatively fixed. Once there are problems such as missing product definition, development omissions, incomplete testing, etc., the terminal data obtained may be incomplete, so that the data product of the network event is illegal. In this case, the developer needs to modify the tracking point code and re-release a new network event version to obtain complete network event data. However, the above method is used to obtain complete network event data, but there are problems such as frequent release of network event versions, long modification cycle, and cumbersome operation.

[0003] When there is a need to add or change data tracking points, both developers and testers must be involved. The entire process is time-consuming and may not meet business needs and operational use. In addition, when the tracking point object is developed and maintained later, if the code and release version of the tracking point object are not changed, the data tracking point cannot be replaced, and the operator cannot legally know the usage of each network event block of the tracking point object, and cannot locate the tracking point object faster and more accurately, and cannot maximize the strengths and avoid the weaknesses of the network event block. Therefore, the data tracking point processing efficiency of the existing data tracking method is low, relatively rigid, inflexible, and difficult to maintain. Summary of the invention

[0004] According to a first aspect of the present invention, the present invention claims a network event processing method for point tracking, characterized in that it includes:

[0005] Obtain access data of the tracking point access record within the preset access domain name type from the tracking point access record data table, and integrate the access data into the candidate event group P1;

[0006] The candidate event group P1 is processed in a standardized manner to obtain a first event group P2 of the buried access record within the preset access domain name type;

[0007] Obtain the hot event group P2n of the buried point access record in the first event group P2, and extract the visited group P2n' of the buried point from the hot event group P2n;

[0008] Set a preset access event of the buried point, and obtain the total of the access event trend element and the periodic access frequency of the buried point in combination with the access frequency of the buried point in the visited group P2n';

[0009] Perform deep learning on the access event trend elements of the buried points and the sum of the periodic access frequencies, and construct an access event trend processing model when the buried point access events increase with the access frequency of the buried points;

[0010] Based on the trend processing model, the trend of the buried point access events recorded in the future communication network frequency is processed.

[0011] According to a second aspect of the present invention, the present invention seeks protection for a network event processing device for point tracking, characterized in that it includes:

[0012] An obtaining unit obtains access data of a point-of-sale access record in a preset access domain name type from a point-of-sale access record data table, and integrates the access data into a candidate event group P1;

[0013] A preprocessing unit performs standard processing on the candidate event group P1 to obtain a first event group P2 of the buried access record within a preset access domain name type;

[0014] A heat extraction unit, which obtains a heat event group P2n of the buried point access record in the first event group P2, and extracts a visited group P2n' of the buried point from the heat event group P2n;

[0015] The integration processing unit sets a preset access event of the buried point, combines the access frequency of the buried point in the visited group P2n', and obtains the total of the access event trend element and the periodic access frequency of the buried point;

[0016] A model building unit performs deep learning on the access event trend elements of the buried points and the sum of the periodic access frequencies, and builds an access event trend processing model when the buried point access events increase with the access frequency of the buried points;

[0017] The processing unit processes the trend of the buried point access event recorded in the future communication network frequency based on the trend processing model.

[0018] According to a third aspect of the present invention, the present invention seeks protection for a network event processing device for point tracking, characterized in that it includes:

[0019] a memory for storing non-transitory computer-readable instructions; and

[0020] A processor is used to access the computer-readable instructions so that the processor implements the network event processing method for point tracking when executing.

[0021] The present invention relates to tracking technology, and specifically to a network event processing method and device for tracking tracking. The tracking trend of tracking access events is processed based on the data of tracking access records in the actual communication network process in the data table. Compared with the tracking event trend elements of the tracking access device in operation, it can more accurately reflect the tracking event trend elements in harsh actual places, and has a stronger guiding significance for actual product development. This method does not need to carry out durability tests on tracking access devices, but processes and handles the access event trend based on the actual communication network data of the access records in the data table, which greatly saves the test cycle and labor costs. This method can realize the tracking trend processing and processing of the corresponding access events of the tracking access device in the preset visited interval, and can be continuously updated as the access frequency of the access record increases, and is easy to operate and highly flexible. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A legal access flow chart of a network event processing method for point tracking involved in the present invention;

[0023] Figure 2 A flowchart of obtaining legal access to the accessed data of a tracking point in a network event processing method for tracking point according to the present invention;

[0024] Figure 3 A flow chart of total access frequency calculation of a network event processing method for point tracking according to the present invention;

[0025] Figure 4 A structural unit diagram of a network event processing device for point tracking according to the present invention;

[0026] Figure 5 This is a device structure diagram of a network event processing device for point tracking involved in the present invention. DETAILED DESCRIPTION

[0027] According to the first embodiment of the present invention, referring to the attached Figure 1 The present invention claims a method for processing network events for point tracking, comprising the steps of:

[0028] P100, obtains the accessed data of the tracking point access record within the preset access domain name type from the tracking point access record data table, and integrates the accessed data into the candidate event group P1;

[0029] P200, standardize the candidate event group P1 to obtain the first event group P2 of the buried access record within the preset access domain name type;

[0030] P300, obtaining the hot event group P2n of the buried point access record in the first event group P2, and extracting the visited group P2n' of the buried point from the hot event group P2n;

[0031] P400, set the preset access event of the buried point, combine the access frequency of the buried point in the visited group P2n', and obtain the total of the access event trend factor and the periodic access frequency of the buried point;

[0032] P500, performs deep learning on the trend elements of buried point access events and the sum of periodic access frequencies, and builds a processing model for the trend of buried point access events when the buried point access frequency increases;

[0033] P600 processes the trend of the buried point access events recorded within the future communication network frequency based on the trend processing model.

[0034] Among them, in this embodiment, the embedding points can be implanted in network products such as websites, APPs, mini-programs, and quick applications.

[0035] Furthermore, step P100 specifically includes:

[0036] The access data of the tracking point access record includes at least the communication network frequency, access record status, communication terminal attributes, tracking point duration and tracking point quantity;

[0037] The access record status includes at least a surface access status and a deep access status;

[0038] The access event of the tracking point at least includes the duration and number of tracking points;

[0039] The above accessed data are integrated into a group form to obtain a candidate event group P1.

[0040] Further, step P200 specifically includes:

[0041] Perform illegal event detection processing on the candidate event group P1. When completely illegal event data is identified in the candidate event group P1, the completely illegal event data is removed. When partially illegal event data is identified in the candidate event group P1, a determination process is performed based on the neighbor access event data.

[0042] A hot event determination process is performed on the candidate event group P1. When there is event data in the candidate event group P1 that meets the hot event condition, determination processing is performed based on the neighbor access event data.

[0043] In this embodiment, when it is identified that there is completely illegal event data in the candidate event group P1, that is, when the entire row is blank, the completely illegal event has no data, and this row is removed;

[0044] When it is identified that there are some illegal event data in the candidate event group P1, among which the communication network frequency and access record status data are not empty, but the relevant data of the buried point is missing, it is judged in combination with the rest of the accessed data that if the access record status is "deep access", no processing is required and the completely illegal event data is retained; if the access record status is "surface access", the completely illegal event data is obviously wrong at this time, and this row is removed;

[0045] When determining and processing hot events, when the data in the candidate event group P1 contains event data that meets the hot event conditions, the completely illegal event has data, but the data value is obviously wrong or unreasonable. For this type of data, it is necessary to determine and process it.

[0046] For further information, see Attachment Figure 2 , step P300, specifically comprising:

[0047] P301, according to the access record status, the access status of the tracking point access record in the preset access domain name type is divided, and multiple activity events of the tracking point access record in the legal communication network interval are extracted to obtain the hot event group P2n of the tracking point access record in the first event group P2;

[0048] P302, obtaining data of the tracking point in the legal access state in the heat event group P2n of multiple tracking point access records, and obtaining the visited interval of the tracking point in the legal access state;

[0049] P303, collect the access event group of the buried points in the visited interval, and combine the communication network frequency of the buried point access record to form the visited group P2n' of the buried point;

[0050] Among them, in this embodiment, the original data exported from the data table is processed by data standardization to form the legal data of the buried point access record in the frequency interval, and the combination is set as P2, and subsequent data processing is performed based on P2;

[0051] Extract the data of the buried point access record in the legal communication network range, where the access record status is "surface access" and "deep access" as the basis for judging the access record communication network;

[0052] In step P301, according to the frequency sequence of the communication network frequency, from the first appearance of "surface access" in the access record state (time t1), until the access record state changes from "surface access" to "deep access" (here, deep access is time t2), that is, the frequency segment from time t1 to time t2, is used as the data of the access record event (the first activity), and this combination is P2.1;

[0053] In step P302, data of the points in each activity event (P2.1, P2.2, P2.3 ... P2.n) in the access record that are in a legal access state are extracted.

[0054] The access records of P2.1, P2.2, P2.3…P2.n are grouped together for each activity event as the hot event group P2n of the buried access records;

[0055] Use the duration and number of tracking points as the basis for judgment, and find the visited intervals where the tracking points are in a legal access state;

[0056] Number of buried comments P = product of the buried duration I and the number of buried comments V;

[0057] In step P303, in the combination of P2.1, according to the frequency order of the communication network frequency, the first time that the number of buried point comments P is greater than 300MB (the judgment value for legal access of the buried point can be 300MB, or it can be set to other event data according to actual needs) is used as the judgment basis (time t3), as the time when the buried point starts legal access. The time when the number of buried point comments P drops below 300MB is used as the time when the buried point stops legal access (time t4). The frequency segment from time t3 to time t4 in the combination of P2.1 is selected as the visited interval where the buried point is in a legal access state, and the combination of this interval is recorded as P2.1'.

[0058] t P2.1’ =t4-t3;

[0059] t P2.1’ Indicates the access frequency of the buried point in the P2.1' combination;

[0060] Furthermore, the visited interval of the tracking point in a legal access state is a frequency interval between when the number of comments is greater than a preset comment number threshold when the tracking point is visited and when the number of comments is lower than a preset comment number threshold when the tracking point is visited;

[0061] When the number of visited comments of a tracking point is greater than the preset comment number threshold, the tracking point is deemed to be in a legal access state.

[0062] For further information, see Attachment Figure 3 , step P400 specifically includes:

[0063] P401, select other access events that are under the preset access event in each visited interval from the visited group P2n';

[0064] P402, based on the communication network frequency of the buried point access record, obtain the sum of the daily access frequency of the buried point in the preset area and the average value of other access events where the buried point is under the preset access event;

[0065] P403, based on the communication network data of the tracking point access record in the preset access domain name type, obtain the tracking point access event trend element when the tracking point access record has an increased access frequency;

[0066] Among them, in this embodiment, in order to process the access event trend of the buried point device, an access event is required, but the legal access interval of the buried point is very large, and it can be legally accessed under different durations, which makes it impossible to unify. Therefore, in order to unify, it is necessary to first determine a specific access interval, such as most of the duration is around 120P, and take the duration of 120P as the preset access event, and obtain the number of buried points under this condition as other access events for subsequent access event trend processing.

[0067] In the above combinations of P2.1', P2.2' to P2.n', data whose duration, quantity or number of comments of the tracking points in each group are in a specific range are selected to obtain data of tracking point access events.

[0068] In this embodiment, in step P402, after multiple data processing steps, the communication network frequency area of ​​the access record is used as the judgment basis to further obtain the area DPy M-N The average value of access events whose embedding points are in a specific interval.

[0069] Specifically, the preset access event in steps P401 and P402 may be any one of the duration, quantity, and number of comments of the tracking point; the other access event may be one or two of the remaining two indicators.

[0070] Step P403 specifically includes:

[0071] Based on the processing of communication network data of buried access records within a certain frequency range, the trend elements of buried access events are obtained as the access frequency of the access records increases.

[0072] For example, DPy1-1, DPy1-2, and DPy1-30 form the distribution of the radiation range in January, indicating that there is activity on every day from January 1 to January 30. If there is no activity on one day, there will be no area corresponding to that day in the combination of tDPy.

[0073] Further, step P500 specifically includes:

[0074] Based on the trend factors of the access events of the tracking points and the total access frequency of the tracking points during the tracking period, the trend and processing formula of the tracking point access events as the access frequency of the access records increases are established according to the optimal linear solution:

[0075]

[0076] in I represents the duration of the tracking event data. sp The corresponding number of buried points and the number of buried point comments, a V , a P They represent the trend coefficient of quantity index and the trend coefficient of comment quantity index respectively, t represents the total visit frequency of the tracking point period, and b V , b P Represents a constant term.

[0077] According to the second embodiment of the present invention, referring to Figure 4 The present invention claims a network event processing device for tracking points, which is characterized by comprising:

[0078] The obtaining unit obtains the accessed data of the access records of the embedded points in the preset access domain name type from the embedded point access record data table, and integrates the accessed data into the candidate event group P1;

[0079] The preprocessing unit performs standard processing on the candidate event group P1 to obtain a first event group P2 of the buried access record within the preset access domain name type;

[0080] A heat extraction unit obtains a heat event group P2n of the buried point access record in the first event group P2, and extracts a visited group P2n' of the buried point from the heat event group P2n;

[0081] The integrated processing unit sets a preset access event of the buried point, combines the access frequency of the buried point in the visited group P2n', and obtains the total of the access event trend factor and the periodic access frequency of the buried point;

[0082] The model building unit performs deep learning on the trend elements of the buried point access events and the sum of the periodic access frequencies, and builds an access event trend processing model when the buried point access events increase with the buried point access frequency;

[0083] The processing unit processes the trend of the buried point access events recorded within the future communication network frequency based on the trend processing model.

[0084] According to the third embodiment of the present invention, referring to Figure 5 The present invention claims a network event processing device for tracking points, which is characterized by comprising:

[0085] a memory for storing non-transitory computer-readable instructions; and

[0086] A processor is used to access computer-readable instructions so that a network event processing method for point tracking is implemented when the processor executes the instructions.

[0087] Those skilled in the art will appreciate that the contents disclosed in this disclosure may be subject to various modifications and improvements. For example, the various devices or components described above may be implemented by hardware, or by software, firmware, or a combination of some or all of the three.

[0088] Flowcharts are used in this disclosure to illustrate the steps of the method according to the embodiments of the present disclosure. It should be understood that the preceding or following steps are not necessarily performed precisely in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes.

[0089] Those skilled in the art will appreciate that all or part of the steps in the above method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk. Optionally, all or part of the steps in the above embodiment can also be implemented using one or more integrated circuits. Accordingly, each unit / unit in the above embodiment can be implemented in the form of hardware or in the form of a software functional unit. The present disclosure is not limited to any particular form of combination of hardware and software.

[0090] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meanings in the immediate vicinity of the relevant art, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0091] The above is an explanation of the present disclosure and should not be considered as a limitation thereof. Although several exemplary embodiments of the present disclosure are described, it will be readily understood by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present disclosure. Therefore, all such modifications are intended to be included within the scope of the present disclosure as defined in the claims. It should be understood that the above is an explanation of the present disclosure and should not be considered to be limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present disclosure is defined by the claims and their equivalents.

[0092] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0093] Although embodiments of the present invention have been shown and described, those skilled in the art will appreciate that various orientations, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

Claims

1. A network event processing method for point tracking, characterized in that: include: Obtain access data of the tracking point access record within the preset access domain name type from the tracking point access record data table, and integrate the access data into the candidate event group P1; The candidate event group P1 is processed in a standardized manner to obtain a first event group P2 of the buried access record within the preset access domain name type; Obtain the hot event group P2n of the buried point access record in the first event group P2, and extract the visited group P2n' of the buried point from the hot event group P2n; Set a preset access event of the buried point, and obtain the total of the access event trend element and the periodic access frequency of the buried point in combination with the access frequency of the buried point in the visited group P2n'; Perform deep learning on the access event trend elements of the buried points and the sum of the periodic access frequencies, and construct an access event trend processing model when the buried point access events increase with the access frequency of the buried points; Based on the trend processing model, the trend of the buried point access events recorded in the future communication network frequency is processed.

2. A network event processing method for point tracking as claimed in claim 1, characterized in that: The step of obtaining access data of the tracking point access record in the preset access domain name type from the tracking point access record data table and integrating the access data into the candidate event group P1 specifically includes: The access data of the tracking point access record includes at least the communication network frequency, access record status, communication terminal attributes, tracking point duration and tracking point quantity; The access record status includes at least a surface access status and a deep access status; The access event of the tracking point at least includes the duration and number of tracking points; The above accessed data are integrated into a group form to obtain a candidate event group P1.

3. A network event processing method for point tracking as claimed in claim 2, characterized in that: The step of performing standard processing on the candidate event group P1 to obtain a first event group P2 of the buried access records within the preset access domain name type specifically includes: The candidate event group P1 is subjected to illegal event detection processing. When it is identified that there are completely illegal event data in the candidate event group P1, the completely illegal event data is removed. When it is identified that there are partially illegal event data in the candidate event group P1, a determination processing is performed based on the neighbor access event data. The candidate event group P1 is subjected to hotspot event determination processing. When there is event data in the candidate event group P1 that meets the hotspot condition, a determination processing is performed based on the neighbor access event data.

4. A network event processing method for point tracking as claimed in claim 3, characterized in that: The step of obtaining the hot event group P2n of the buried point access record in the first event group P2 and extracting the visited group P2n' of the buried point from the hot event group P2n specifically includes: Divide the access status of the buried access record in the preset access domain name type according to the access record status, extract multiple activity events of the buried access record in the legal communication network interval, and obtain the hot event group P2n of the buried access record in the first event group P2; Acquire data of the tracking point being in a legal access state in the heat event group P2n of the tracking point access records for multiple times, and obtain the visited interval of the tracking point being in a legal access state; The access event group of the buried point within the visited interval is collected, and the visited group P2n' of the buried point is formed in combination with the communication network frequency of the buried point access record.

5. A network event processing method for point tracking as claimed in claim 4, characterized in that: The visited interval of the tracking point in a legal access state is the visited interval between when the tracking point has been visited and the number of comments is greater than the preset comment number threshold and when the tracking point has been visited and the number of comments is lower than the preset comment number threshold; The state where the number of visited comments of the tracking point is greater than the preset comment number threshold is determined as the tracking point being in a legal access state.

6. A network event processing method for point tracking as claimed in claim 4, characterized in that: The setting of the preset access event of the buried point, combined with the access frequency of the buried point in the visited group P2n', to obtain the total of the access event trend element and the periodic access frequency of the buried point specifically includes: selecting other access events of the buried point under the preset access event in each visited interval from the visited group P2n'; Based on the communication network frequency of the tracking point access record, the sum of the daily access frequency of the tracking point in the preset area and the average value of other access events of the tracking point under the preset access event are obtained; based on the communication network data of the tracking point access record in the preset access domain name type, the access event trend elements of the tracking point when the access frequency of the tracking point access record increases are obtained.

7. A network event processing method for point tracking as claimed in claim 6, characterized in that: The communication network data based on the buried point access record within the preset access domain name type is used to obtain the access event trend elements of the buried point when the access frequency of the buried point access record increases, specifically including: obtaining the radiation range of the buried point access record, and obtaining the total daily access frequency and the total periodic access frequency of the buried point in a legal access state within the radiation range.

8. A method for processing network events for point tracking as claimed in claim 4, characterized in that: The deep learning of the access event trend elements and the sum of the periodic access frequencies of the buried points is performed to construct a trend processing model for buried point access events when the access frequency of the access records increases, specifically including: Based on the trend factors of the access events of the tracking points and the total access frequency of the tracking points during the tracking period, the trend and processing formula of the tracking point access events as the access frequency of the access records increases are established according to the optimal linear solution: in I represents the duration of the tracking event. sp The corresponding number of buried points and the number of buried point comments, a V , a P They represent the trend coefficient of quantity index and the trend coefficient of comment quantity index respectively, t represents the total visit frequency of the tracking point period, and b v , b p Represents a constant term.

9. A network event processing device for point tracking, characterized in that: include: An obtaining unit obtains access data of a point-of-sale access record in a preset access domain name type from a point-of-sale access record data table, and integrates the access data into a candidate event group P1; A preprocessing unit performs standard processing on the candidate event group P1 to obtain a first event group P2 of the buried access record within a preset access domain name type; A heat extraction unit, which obtains a heat event group P2n of the buried point access record in the first event group P2, and extracts a visited group P2n' of the buried point from the heat event group P2n; The integration processing unit sets a preset access event of the buried point, combines the access frequency of the buried point in the visited group P2n', and obtains the total of the access event trend element and the periodic access frequency of the buried point; A model building unit performs deep learning on the access event trend elements of the buried points and the sum of the periodic access frequencies, and builds an access event trend processing model when the buried point access events increase with the access frequency of the buried points; The processing unit processes the trend of the buried point access event recorded in the future communication network frequency based on the trend processing model.

10. A network event processing device for point tracking, characterized in that: include: a memory for storing non-transitory computer-readable instructions; as well as A processor is used to access the computer-readable instructions so that when the processor executes, it implements a network event processing method for point tracking as described in any one of claims 1-8.

Images