A method and apparatus for identifying automatic communication programs

By calculating the session time information and parameter value deviation of the automatic communication program, the recognition problem caused by the changing artificial intelligence voice conversation patterns is solved, achieving efficient and accurate automatic communication program recognition, and reducing resource consumption and security risks.

CN116962480BActive Publication Date: 2026-11-17CHINA MOBILE GROUP SICHUAN +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202211263057.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-10-14
Publication Date
2026-11-17
Estimated Expiration
2042-10-14

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately identify automated communication programs, especially given the varied patterns of AI-powered voice conversations. Traditional recognition rules are ineffective in identifying automated communication programs, leading to security risks and resource waste.

Method used

By acquiring multiple session time information from the communication program, the average session establishment interval is calculated, and the sampling time length is determined based on this. The deviation of the session parameter values ​​is used to determine whether it is an automatic communication program.

Benefits of technology

It improves the accuracy and efficiency of automatic communication programs, reduces resource consumption, lowers the probability of false detections and missed detections, and enhances communication security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116962480B_ABST
    Figure CN116962480B_ABST
Patent Text Reader

Abstract

This invention discloses a method and apparatus for identifying automatic communication programs, addressing the problem of inaccurate identification of such programs. The solution provided includes: acquiring communication data of the communication program to be identified, the communication data including time information of multiple sessions established by the communication program; determining the average session establishment interval duration in the communication data based on the time information of the multiple sessions; sampling the communication data based on the average session establishment interval duration to obtain a sampling result, wherein the sampling time is greater than or equal to the sum of a preset number of average session establishment interval durations; if the deviation of the parameter values ​​of the sessions established by the communication program in the sampling result is less than a preset deviation, then the communication program is determined to be an automatic communication program, thereby efficiently and accurately identifying automatic communication programs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of communications, and more particularly to a method and apparatus for identifying automatic communication programs. Background Technology

[0002] In the field of communications, to meet the established user or operational needs, automated communication programs that use code programming to achieve automatic communication, response, and interaction have emerged in the network. Examples include customer service robots, virtual dialers, and intelligent answering programs.

[0003] The private information of some communication users, such as their communication accounts, may be collected and used by criminals to communicate with users through the aforementioned automated communication programs. This not only wastes the communication users' time but also poses security risks such as fraud.

[0004] Due to the rapid development of artificial intelligence, the conversation patterns, durations, and content of automated communication programs are constantly changing, making it difficult for traditional recognition rules to accurately identify automated communication programs.

[0005] How to improve the accuracy of identifying automatic communication programs is the technical problem that this application aims to solve. Summary of the Invention

[0006] The purpose of this application is to provide a method and apparatus for identifying automatic communication programs, so as to solve the problem of inaccurate identification of automatic communication programs.

[0007] Firstly, a method for identifying automatic communication programs is provided, including:

[0008] Acquire communication data of the communication program to be identified, the communication data including time information of multiple sessions established by the communication program;

[0009] The average session establishment interval in the communication data is determined based on the time information of the multiple sessions;

[0010] The communication data is sampled based on the average session establishment interval to obtain the sampling result of the communication data, wherein the sampling time of the communication data is greater than or equal to the sum of a preset number of average session establishment intervals;

[0011] If the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation, then the communication program is determined to be an automatic communication program.

[0012] Secondly, an apparatus for identifying an automatic communication program is provided, comprising:

[0013] The acquisition module acquires the communication data of the communication program to be identified, the communication data including the time information of multiple sessions established by the communication program;

[0014] The determining module determines the average session establishment interval duration in the communication data based on the time information of the multiple sessions;

[0015] The sampling module samples the communication data based on the average session establishment interval duration to obtain the sampling result of the communication data, wherein the time length for sampling the communication data is greater than or equal to the sum of a preset number of the average session establishment interval durations;

[0016] If the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation, the identification module determines that the communication program is an automatic communication program.

[0017] Thirdly, an electronic device is provided, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method of the first aspect.

[0018] Fourthly, a computer-readable storage medium is provided on which a computer program is stored, which, when executed by a processor, implements the steps of the method of the first aspect.

[0019] In this embodiment, communication data of a communication program to be identified is acquired, including time information of multiple sessions established by the communication program. The average session establishment interval in the communication data is determined based on the time information of the multiple sessions. The communication data is then sampled based on the average session establishment interval to obtain a sampling result, wherein the sampling time is greater than or equal to the sum of a preset number of average session establishment intervals. If the deviation of the parameter values ​​of the sessions established by the communication program in the sampling result is less than a preset deviation, the communication program is determined to be an automatic communication program. Determining the sampling time based on the average session establishment interval ensures that the sampling result fully expresses the communication behavior performed by the communication program, thereby effectively identifying whether the communication program is an automatic communication program. Furthermore, this solution, by determining the sampling time based on the average session establishment interval, improves identification efficiency and avoids excessively long sampling times that consume processing resources. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings:

[0021] Figure 1 This is one of the flowcharts illustrating a method for identifying an automatic communication program according to an embodiment of the present invention.

[0022] Figure 2 This is a second schematic flowchart of a method for identifying automatic communication programs according to an embodiment of the present invention.

[0023] Figure 3 This is a flowchart of a method for identifying automatic communication programs according to an embodiment of the present invention.

[0024] Figure 4 This is a fourth flowchart illustrating a method for identifying automatic communication programs according to an embodiment of the present invention.

[0025] Figure 5 This is the fifth flowchart of an embodiment of the present invention, illustrating a method for identifying automatic communication programs.

[0026] Figure 6 This is a flowchart of an embodiment of the present invention, a method for identifying automatic communication programs.

[0027] Figure 7 This is a schematic diagram of the structure of a device for identifying automatic communication programs, according to an embodiment of the present invention. Detailed Implementation

[0028] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. The drawing numbers in this application are only used to distinguish the various steps in the solution and are not used to limit the execution order of the various steps. The specific execution order is as described in the specification.

[0029] In the field of communications, in cases of fraudulent harassment using automated communication programs, one common behavioral characteristic of these programs is that they mechanically generate communications and send data content in a fixed format at specific time intervals. The more stable the session interval, the greater the probability that the session is a programmatic automated communication.

[0030] As automated communication programs become increasingly intelligent, they can automatically adjust session intervals, leading to decreased accuracy in identifying such programs. If the heartbeat interval is modified mid-program, effective identification of automated communication behavior becomes difficult. Furthermore, the different environments, services, and roles of the communicating parties in network communication result in varying communication patterns. For example, in areas with poor signal, network communication might employ short, rapid sessions. During network service communication, a normal conversational communication pattern might be used. When the communicating parties are in a close relationship, a longer communication period might be necessary. Due to these diverse communication patterns and varying behavioral characteristics, it is difficult to effectively identify automated communication programs using fixed rules.

[0031] To address the problems existing in the prior art, embodiments of this application provide a method for identifying automatic communication programs, such as... Figure 1 As shown, it includes:

[0032] S11: Obtain communication data of the communication program to be identified, the communication data including time information of multiple sessions established by the communication program.

[0033] In this example, it is assumed that the communication program is installed on a user terminal with communication capabilities. The communication data of the communication program may include TCP (Transmission Control Protocol) communication data. In practical applications, the TCP communication data of the user terminal can be identified through features such as protocol mode and field information. Alternatively, auxiliary tools such as monitoring programs or plugins can be used to detect when the user terminal starts the communication program and then extract the communication data from the started communication program.

[0034] The communication data specifically includes the start time of the communication program establishing a session. In addition, it may also include other communication information such as the duration of the session and the end time.

[0035] The aforementioned sessions are typically established between terminals, enabling communication between them. In this example, the communication data includes time information for multiple sessions actively established by the communication program. This time information characterizes the session execution features of the communication program, thereby determining its communication behavior characteristics and facilitating accurate identification of whether the program is performing automatic communication behavior.

[0036] S12: Determine the average session establishment interval in the communication data based on the time information of the multiple sessions.

[0037] Among them, the session establishment interval refers to the time length between adjacent session establishment times, and the average session establishment interval refers to the average of multiple adjacent session establishment intervals.

[0038] In practical applications, the average session establishment interval can be determined based on a pre-set duration of communication data. For example, one minute of communication data can be extracted, and the average session establishment interval can be determined based on the times when sessions are established within that minute. If the number of sessions contained in one minute of communication data is too small, the above time length can be extended according to the actual situation to determine an average session establishment interval that matches the actual situation.

[0039] For example, sessions can be sorted in ascending order of their network frame establishment times, i.e., sorted according to the order of establishment time. The network frame time of sequence number n is subtracted from the network frame time of sequence number n-1. For example, the network frame time of sequence number n=2 is subtracted from the network frame time of sequence number n=1. This process is repeated, incrementing by 1 each time until n=6, to iterate through all sessions and calculate the average (avg) of the establishment intervals of the first preset number (5 in this example), which is the average session establishment interval.

[0040] S13: Sample the communication data based on the average session establishment interval duration to obtain the sampling result of the communication data, wherein the time length for sampling the communication data is greater than or equal to the sum of a preset number of the average session establishment interval durations.

[0041] After determining the average session establishment interval of the communication program through the above steps, the sampling time length adapted to the communication program can be determined based on a preset number. This sampling time length is greater than or equal to the sum of the preset number of average session establishment intervals. For example, assuming the preset number is 5, then the sampling time length is not less than 5 times the average session establishment interval.

[0042] By performing sampling at the time length determined in this step, it is ensured that multiple sessions are sampled, so that the sampling results can fully express the characteristics of multiple sessions of the communication program, which is helpful for analyzing and determining whether the communication program has performed automatic communication behavior.

[0043] S14: If the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than the preset deviation, then the communication program is determined to be an automatic communication program.

[0044] In this step, the sampling results are used to determine whether the communication program is an automatic communication program. The parameter values ​​of the session established by the communication program can characterize the communication behavior. Optionally, the parameter values ​​of the session established by the communication program include at least one of the following:

[0045] The time interval between establishing adjacent sessions, the capacity of data packets sent by the communication program in the session, the number of data packets sent by the communication program in the session, and the time interval between sending adjacent data packets sent by the communication program in the session.

[0046] The time interval between the establishment of adjacent sessions characterizes the communication behavior of the communication program in establishing a session. The capacity and number of data packets sent by the communication program during a session, as well as the time interval between the transmission of adjacent data packets, characterize the communication behavior of the communication program during the session.

[0047] In this step, an automatic communication program can be identified based on the deviation of any parameter value. Deviation refers to the difference between an observed value or test score and a specific reference point, also known as "deviation from the mean." It is a measure of the degree of dispersion of the values ​​of a random variable (i.e., a set of data) about a central value. In this example, deviation can refer to the difference between the maximum value and the mean, and the difference between the minimum value and the mean, both falling within a preset range. In this example, the deviation indicates the degree of dispersion of the parameter value distribution. If the deviation is within the preset range, it indicates that the corresponding parameter values ​​are converging, and the communication program can be identified as an automatic communication program.

[0048] Taking the establishment time interval of adjacent sessions as an example, the establishment times of adjacent sessions in multiple sessions in the sampling results are statistically analyzed to determine the maximum interval time, minimum interval time, and average interval time. If the difference between the maximum interval time and the average interval time is within a preset range, and moreover, the difference between the average interval time and the minimum interval time is also within a preset range, it can be determined that the time intervals for establishing sessions of the communication program are similar, that is, the communication program has performed automatic communication behavior, and thus it can be determined that the communication program is an automatic communication program.

[0049] As automated communication behaviors become increasingly intelligent, and calls using AI-powered voice interaction are highly variable, it is difficult to identify them based on fixed rules. Therefore, this solution first determines an appropriate sampling time based on the average session establishment interval to ensure that the sampling results can express sufficient communication behavior characteristics, and then identifies automated communication programs based on the sampling results. For terminals using AI-powered voice interaction, this solution can effectively improve the accuracy of identifying automated communication programs. For identified automated communication programs, corresponding auxiliary communication measures can be implemented to reduce communication risks for users. The solution provided in this application, which determines the sampling time based on the average session establishment interval, ensures that the sampling results can fully express the communication behavior executed by the communication program, thereby effectively identifying whether a communication program is an automated communication program. Moreover, this solution, by determining the sampling time based on the average session establishment interval, helps improve recognition efficiency and avoids excessively long sampling times that consume processing resources.

[0050] The sampling duration in this embodiment can be determined based on the number of reference sessions. Based on the example given in this embodiment, the average session establishment interval is determined according to the time of session establishment within one minute. Based on the communication data of this minute, the number of sessions *m* contained in this minute's communication data can be further determined, where *m* is a non-zero integer. Assuming the preset number is 5, the sampling duration is no less than 5 *m* session durations. In this example, 5 *m* is referred to as the number of reference sessions. Generally, the duration of a communication program session can be long or short. The longer the duration of a single session, the more communication features can be collected during the session, and the fewer sessions need to be collected. For example, for a long-duration session, the number of reference sessions can be determined to be 4 *m*, and for a short-duration session, the number of reference sessions can be determined to be 6 *m*. Optionally, after determining the above-mentioned number of reference sessions, the product of the number of reference sessions and the average session establishment interval can be used to determine the sampling.

[0051] Based on the solutions provided in the above embodiments, optionally, such as Figure 2 As shown, step S13 above includes:

[0052] S21: Determine the session pattern that matches the communication data based on the average session establishment interval.

[0053] In this example, the session mode indicates the length of a session executed by the corresponding communication program. For instance, if the average session establishment interval is less than 1 second, the communication data of the program is determined to match the short session communication mode. If the average session establishment interval is greater than 3600 seconds, the communication data of the program is determined to match the long session communication mode. The correspondence between session mode and average session establishment interval can be preset. In practical applications, there can be more types of session modes, such as normal session mode, short-to-medium session mode, and medium-to-long session mode.

[0054] S22: If the average session establishment interval is less than or equal to the preset interval, then the communication data is presampled using the preset sampling duration corresponding to the session mode to obtain the presampled result.

[0055] The preset interval duration can be set in advance according to the actual situation. In this embodiment, it is assumed that the preset interval duration is 3600 seconds. If the session establishment interval duration is too long, it will take more time to perform processing and analysis, and it will also require the collection of samples with a longer duration. It will be difficult to effectively identify the communication program based on the relevant characteristics of the session establishment interval. Therefore, in this step, the communication program with an average session establishment interval duration not greater than the preset interval duration will be presampled using the preset sampling duration corresponding to the session mode.

[0056] The preset sampling duration for each session mode can be pre-set according to actual conditions. Generally speaking, the longer the session represented by the session mode, the longer the sampling duration can be preset. For example, for short session communication mode, the corresponding preset sampling duration can be 5 minutes. For normal session communication mode (i.e., communication mode with session length between short and long session communication), the corresponding preset sampling duration can be (avg*5m) / 3600+1 seconds.

[0057] S23: Determine the sampling duration for sampling the communication data based on the number of sessions contained in the pre-sampling results.

[0058] In this step, the actual sampling duration is determined based on the pre-sampling results. The pre-sampling results can be used to determine whether the results obtained from sampling with the preset sampling duration can fully characterize the communication behavior features, and then a more reasonable sampling duration can be determined based on the preset sampling duration.

[0059] For example, if the number of sessions included in the presampling results is too small, such as less than 5m sessions, it indicates that the presampling results obtained by performing presampling with a preset sampling duration contain insufficient communication behavior features, and therefore cannot accurately identify whether the communication program has performed communication behavior. Therefore, a longer sampling duration can be determined based on the preset sampling duration used for presampling. For example, the duration of 5m sessions in the communication data can be determined as the sampling duration for performing the sampling.

[0060] If the number of sessions contained in the pre-sampling results is too large, the sampling time can be appropriately shortened according to the actual situation to improve recognition efficiency and reduce processing resource consumption.

[0061] If the number of sessions included in the pre-sampling results is within a reasonable range, the preset sampling duration can be directly determined as the sampling duration. This reasonable range can be preset, for example, it can be 5m to 7m, to determine whether the duration used for pre-sampling can sample sufficient communication behavior characteristics.

[0062] S24: Sample the communication data for the specified sampling duration to obtain the sampling result of the communication data.

[0063] The solution provided in this application determines a more reasonable sampling duration by determining a preset sampling duration and performing pre-sampling, so as to ensure that the actual sampling results can represent sufficient communication behavior features, so as to accurately and effectively identify whether the communication program has performed automatic communication behavior.

[0064] Based on the solutions provided in the above embodiments, optionally, such as Figure 3 As shown, step S23 above includes:

[0065] S31: If the number of sessions included in the pre-sampling result is less than or equal to the preset number, then the sum of the preset number of average session establishment intervals is determined as the sampling duration for the communication data sampling.

[0066] S32: If the number of sessions contained in the pre-sampling result is greater than the preset number, the preset sampling duration is determined as the sampling duration for the communication data to be sampled.

[0067] In the solution provided in this application embodiment, the sampling duration for actual sampling can be determined based on the aforementioned preset quantity. Specifically, if the number of sessions included in the pre-sampling result is less than or equal to the preset quantity, it indicates that the pre-sampling result contains fewer communication behavior features. Therefore, the product of the preset quantity and the average session establishment interval can be determined as the sampling duration for communication data sampling to ensure that the sampling result obtained contains sufficient communication behavior features.

[0068] If the number of sessions included in the above presampling results is greater than the preset number, it indicates that the preset sampling duration used in the above presampling has been able to sample sufficient communication behavior features, and thus the preset sampling duration can be directly determined as the sampling duration for the actual execution of communication data sampling.

[0069] The solution provided by the embodiments of this application can determine a reasonable sampling duration based on the pre-sampling results, so as to ensure that the sampling results obtained by the actual sampling can contain sufficient communication behavior characteristics.

[0070] For example, when the average duration (avg) is less than 1 second, the communication mode can be determined to be short session communication. Generally, short session communication is more likely to be automatic communication behavior, therefore, it is necessary to speed up the sampling and identification process to quickly alert relevant users and reduce potential losses. In this case, to ensure that as many session features as possible are acquired, it can be determined whether the duration of the first 5m sessions of the current communication exceeds the preset sampling time length for the corresponding mode, or in other words, whether there are 5m sessions within 5 minutes. If the duration exceeds the preset sampling time length, or the number of sessions within 5 minutes is less than 5m, the sampling time can be determined as the duration of the first 5m sessions. If it does not exceed the preset duration, or the number of sessions within 5 minutes is greater than or equal to 5m, the sampling time is determined as the aforementioned pre-sampling time.

[0071] For example, when the average value is greater than or equal to 120 seconds and less than 3600 seconds, the communication mode can be determined to be normal session communication. To round off the sampling time range for easier control, and to ensure that as many communication features as possible are acquired, the sampling time for normal session communication can be determined as follows:

[0072] Determine whether the duration of the first 5m sessions exceeds the preset sampling time length for normal session communication mode: (avg*5m) / 3600+1 seconds, or in other words, whether the preset sampling time includes more than 5m sessions. If it exceeds or includes more than 5m sessions, the sampling time is determined to be the duration of the first 5m sessions; if it does not exceed, the sampling time is determined to be (avg*5m) / 3600+1 seconds, which is the preset sampling time length corresponding to normal session mode.

[0073] This step determines a reasonable sampling duration, avoiding the use of a fixed sampling method. Sampling based on a reasonable duration ensures that the sampling results contain sufficient communication behavior features, thereby achieving more accurate communication behavior judgments with lower system overhead. This improves the applicability of automatic communication behavior recognition and enhances system resource utilization efficiency.

[0074] Based on the solution provided in the above embodiments, optionally, step S14 includes:

[0075] If the difference in the time interval between the establishment of adjacent sessions in the sessions established by the communication program in the sampling results is less than the preset inter-session isolation difference, and the difference in the capacity of the data packets sent by the communication program in the sessions established by the communication program in the sampling results is less than the preset data packet capacity difference, and the difference in the number of data packets sent by the communication program in the sessions established by the communication program in the sampling results is less than the preset number of data packets difference, then the communication program is determined to be an automatic communication program.

[0076] The solution provided in this application detects automatic communication behavior from two aspects to determine whether the communication program has performed automatic communication behavior. One aspect is detection based on the session establishment time interval, and the other aspect is detection based on the number of data packets and bytes during the communication process.

[0077] In the step of detecting the number of data packets and bytes in the communication process, optionally, the maximum, minimum and average values ​​of the number of data packets and bytes sent by the client and server in each session are calculated using the client identifier, server identifier and server port as primary keys, so as to determine the deviation of the corresponding parameter values.

[0078] Specifically, the deviation of the capacity of data packets sent by the communication program in the session established by the communication program in the sampling results is determined based on the difference between the maximum capacity and the average capacity of the data packets sent by the communication program, and the difference between the average capacity and the minimum capacity of the data packets sent by the communication program. If the deviation is less than the preset data packet capacity deviation, it indicates that the communication behavior performed by the communication program in the dimension of the data packet capacity is convergent. In other words, the communication program performs automatic communication behavior in the behavior of sending data packet capacity.

[0079] Correspondingly, the number of data packets is determined in a similar way to the data packet capacity mentioned above. Here, the number of data packets refers to the number of data packets in the sampling results, per session. The deviation of the number of data packets sent by the communication program in the session established by the communication program in the sampling results is determined based on the difference between the maximum and average number of data packets sent by the communication program, and the difference between the average and minimum number of data packets sent by the communication program. If this deviation is less than the preset data packet number deviation, it indicates that the communication behavior performed by the communication program is convergent in terms of the number of data packets sent. In other words, the communication program performs automatic communication behavior in the dimension of the number of data packets sent.

[0080] Regarding the establishment time interval, based on the establishment times of multiple sessions in the sampling results, the establishment time interval of adjacent sessions is determined, and the maximum, minimum, and average values ​​of this establishment time interval are identified. The deviation of the establishment time interval between adjacent sessions is determined based on the difference between the maximum and average establishment time intervals of adjacent sessions, and the difference between the average and minimum establishment time intervals of adjacent sessions. If this deviation is less than the preset inter-session isolation difference, it indicates that the communication behavior performed by the communication program is convergent in terms of the adjacent session establishment time interval characteristic; in other words, the communication program performs automatic communication behavior in the dimension of adjacent session establishment time interval.

[0081] The solution provided in this application identifies whether a communication program has performed automatic communication behavior based on three dimensions: the time interval between the establishment of adjacent sessions, the number of data packets sent, and the capacity of the data packets sent. If the communication program performs automatic communication behavior in all three dimensions, it can be determined that the communication program is an automatic communication program, which can effectively improve the efficiency and accuracy of identifying automatic communication programs.

[0082] In practical applications, the automatic communication behavior of AI-based voice-based automated communication programs may vary. A small number of specific sessions within a larger pool may not meet the rules for automatic communication behavior described above. Optionally, for cases where the automatic communication program cannot be identified using the above rules, it can be further determined whether the proportion of data satisfying the rules in each dimension exceeds a preset proportion. Taking the establishment time interval between adjacent sessions as an example, assuming that more than 90% of the data in the sampling results have an adjacent session establishment time interval that meets the rules for automatic communication behavior, it can be determined that the communication program has performed automatic communication behavior. Correspondingly, preset proportions can also be set for the dimensions of data packet capacity and data packet quantity to determine whether the communication program as a whole has performed automatic communication behavior.

[0083] The solution provided in this application can effectively identify flexible and varied automatic communication programs. When more than a preset percentage of data meets the rules of automatic communication behavior, it can be determined that the communication behavior executed by the program is automatic, and thus the program itself is identified as an automatic communication program. Determining whether the overall communication behavior executed by the program is stable or regular can avoid the impact of normal small-scale data fluctuations due to network communication protocol auto-filling in some sporadic cases on the accuracy of the judgment, thus reducing missed detections and improving the accuracy of automatic communication behavior identification.

[0084] Based on the solutions provided in the above embodiments, optionally, such as Figure 4 As shown, step S13 above includes:

[0085] S41: If the average session establishment interval is longer than the preset interval, the communication data is sampled at the preset sampling duration corresponding to the session mode to obtain the sampling result of the communication data.

[0086] In this embodiment, the preset interval duration is, for example, 3600 seconds. For communication data with an average session establishment interval duration longer than this preset interval duration, due to the excessively long session interval, if the relevant features of the session interval are used to perform automatic communication behavior identification, a large amount of data needs to be sampled, which may reduce the identification efficiency of the automatic communication program and often consume a lot of data processing resources.

[0087] Based on this, this scheme determines that the corresponding session mode is a long session communication mode when the average session establishment interval is longer than the preset interval, and then samples the communication data based on the preset sampling duration. Since the session duration is relatively long in the communication data of the long session communication mode, the sampling results obtained by performing sampling based on the preset sampling duration can characterize the communication behavior features in the continuous session.

[0088] Step S14 above includes:

[0089] S42: If the difference in the transmission time interval between adjacent data packets sent by the communication program in the session established by the communication program in the sampling result is less than the preset data packet isolation difference, then the communication program is determined to be an automatic communication program.

[0090] For example, if the sampling results show that the transmission frequency of adjacent data packets sent by the communication program is similar, that is, the difference in the transmission time interval of adjacent data packets is less than the preset isolation difference between data packets, then it can be determined that the session is a heartbeat session, and thus it can be determined that the communication program is an automatic communication program.

[0091] Optionally, further identification can be made based on the data packet capacity in the sampling results. For example, if the difference in the transmission time interval between adjacent data packets sent by the communication program is less than the preset data packet isolation difference, and the difference in the capacity of the data packets sent by the communication program is less than the preset data packet capacity difference, then the communication program is determined to be an automatic communication program.

[0092] The solution provided by the embodiments of this application identifies whether the communication program has performed automatic communication behavior based on the sending time interval of data packets in a continuous session for communication data with long session duration, thereby avoiding excessive consumption of processing resources and achieving effective identification of automatic communication programs.

[0093] Based on the solutions provided in the above embodiments, optionally, such as Figure 5 As shown, before step S12 above, the following steps are also included:

[0094] S51: Obtain the data information of each session in the communication data, and obtain the metadata corresponding to each session respectively. The metadata field information includes the session start time and at least one of the following: client identifier, server identifier, server port information, total number of bytes sent by the client, total number of bytes sent by the server, number of data packets sent by the client, and number of data packets sent by the server.

[0095] Specifically, the client identifier can be the client's IP (Internet Protocol Address), and the server identifier can be the server's IP address.

[0096] S52: Generate metadata logs based on the metadata corresponding to each session.

[0097] Step S12 above includes:

[0098] S53: Determine the average session establishment interval duration in the communication data based on metadata including the session start time.

[0099] The metadata logs generated in this embodiment facilitate alerting and restricting identified automated communication programs. For applications deemed risky, sessions can be terminated, effectively improving security. The following examples further illustrate this solution.

[0100] like Figure 6 As shown, firstly, TCP traffic is collected. Specifically, the Ethernet traffic in the communication of the communication program to be identified is analyzed and processed to extract TCP protocol communication data information from the traffic in order to construct a metadata log.

[0101] This step can identify TCP protocol communication data in the current terminal traffic using existing known technologies such as protocol modes and field information. Alternatively, it can be achieved by using monitoring programs or plugins to detect when a user terminal has started a corresponding communication program and extracting the traffic data of that program. After decoding this data, based on each session, corresponding data information is extracted from each communication data field to construct corresponding metadata. The fields for each metadata element include information corresponding to different sessions: client IP, server IP, server port, session start time, total bytes sent by the client, total bytes sent by the server, number of data packets sent by the client, and number of data packets sent by the server. Finally, multiple metadata elements are used to construct a metadata log corresponding to the communication of the communication program.

[0102] Then, the session interval is calculated. Specifically, the session establishment interval and the number of reference sessions in the communication process are determined based on the metadata logs, thereby determining the sampling time applicable to the communication program.

[0103] The reference session in this step refers to the session that provides communication characteristics during the automatic communication behavior judgment. The number of reference sessions mentioned above refers to the total number of the aforementioned reference sessions, that is, the number of sessions that provide communication characteristics.

[0104] Because the communication characteristics of normal communication and automated machine communication vary more significantly with the duration of the session, a longer sampling time and a larger number of reference sessions collected result in more comparative features, leading to a more accurate final judgment.

[0105] However, if the sampling time is too long, the larger the number of reference sessions collected, the more severe the impact on the execution efficiency of this scheme will be. Therefore, this scheme determines a sampling time appropriate for different communication session conditions.

[0106] The number of reference sessions obtained at the same sampling time varies under different communication session modes, which also affects the number of communication features sampled. Therefore, the number of reference sessions can be used to optimize the sampling time when determining the sampling time, so as to sample as many communication behavior features as possible during the communication process while ensuring recognition efficiency.

[0107] Subsequently, it is determined whether the deviation of the parameter values ​​of the session established by the communication program is less than the preset deviation, thereby identifying whether the communication program is an automatic communication program.

[0108] If so, the communication traffic generated by the automatic communication behavior can be further identified based on the data packet capacity and number of data packets, and the initiator of the automatic communication behavior can be identified so as to implement corresponding measures in a targeted manner.

[0109] If not, we can further identify whether there is regular communication traffic with time intervals. If some of the communication traffic is regular, we can further identify the data packet size and number of data packets in this regular traffic, and then determine the initiator of the identified automatic communication behavior and then implement corresponding measures.

[0110] Finally, appropriate auxiliary communication measures can be determined based on the number (or percentage) of sessions that conform to the automatic communication behavior rules.

[0111] If an automatic communication program is identified, corresponding communication measures can be implemented against it. For example, for communication between the client and the server, this step can count the number of sessions (hereinafter referred to as automatic communication sessions) generated on the client and server respectively according to the above process that belong to automatic communication behavior. The number of client automatic communication sessions and server automatic communication sessions are summed, and corresponding auxiliary communication measures are determined based on the client sum (or client ratio, i.e., the ratio of the client sum to the total number of sessions) and the server sum (or server ratio, i.e., the ratio of the server sum to the total number of sessions).

[0112] For example, when the sum or ratio indicates that the number of automatic communication sessions in the current target communication process is small (e.g., the total number of sessions is 30, the client sum is less than or equal to 10, or the client ratio is less than or equal to 30%), an alarm message can be sent to the server to remind that there is automatic communication behavior in the current communication process, and the server can perform subsequent communication processing as needed.

[0113] When the sum or ratio represents the number of automatic communication sessions in the current target communication process in an intermediate state (e.g., the total number of sessions is 30, the client sum is greater than 10 and less than or equal to 20, or the client ratio is greater than 30% and less than or equal to 65%), an alarm message can be sent to the server to remind that there are a certain number of automatic communication behaviors in the current communication process. The alarm message also provides an instruction to choose whether to terminate the communication immediately.

[0114] When the sum or ratio indicates that the number of automatic communication sessions in the current target communication process is in a large state (e.g., the total number of sessions is 30, the sum of clients is greater than 20, or the ratio of clients is greater than 65%), the system can automatically terminate the communication, add the clients to the blacklist, and include the metadata logs corresponding to the target communication in the traceable record.

[0115] In summary, the solution provided in this application analyzes and processes traffic in communication to obtain the average (avg) of the adjacent session establishment interval within one minute and the reference session count (5m) of the communication program to be identified. Based on the average (avg), the call mode of the target communication is determined, and then a sampling time applicable to the communication program is determined based on the preset sampling time length corresponding to the call mode and the reference session count (5m). After sampling is performed according to the second sampling time to obtain the sampling results, information such as the adjacent session establishment interval, the number of packets sent, and the number of bytes sent on different ends are calculated. Whether the session establishment interval, the number of packets sent, and the number of bytes sent are similar is used to determine whether the communication program has performed communication behavior. Furthermore, the proportion of sessions with automatic communication behavior in the total number of sessions can be determined. Finally, based on the number (or proportion) of automatic communication sessions on different ends, the end performing automatic communication and its severity can be determined, and corresponding auxiliary communication measures can be taken. Specifically, the measures may include: sending alarm information reminding users of the existence of automatic communication behavior during the current communication process; providing instructions to choose whether to immediately terminate the communication; the system automatically terminating the communication and adding the corresponding end to the blacklist; and including the corresponding metadata log in traceable records.

[0116] The proposed method can determine the sampling time applicable to different communication modes, thereby collecting corresponding communication behavior characteristics for different communication conditions. This achieves more accurate communication behavior judgment results with lower system overhead, improving the accuracy of automatic communication behavior identification and increasing system resource utilization efficiency. Furthermore, the solution provided in this embodiment can also identify the corresponding automatic communication behavior origin from the time interval between adjacent sessions, the number of packets sent, and the number of bytes sent, and take corresponding auxiliary communication measures based on the number (or proportion) of automatic communication sessions on different ends, reducing the probability of false positives and false negatives in automatic communication behavior detection and improving the level of intelligent automatic processing.

[0117] The solution provided in this application is highly applicable to the identification of automated communication devices such as PLCs (Programmable Logic Controls) and DCSs (Distributed Control Systems) in all industrial production environments. It can accurately identify control devices conducting automated communication within large production areas of industrial control environments. Furthermore, the technical basis of this solution aligns well with the natural characteristics of industrial control environments, exhibiting high accuracy in detecting abnormal network operation status of automated communication devices. It can be widely applied to various communication scenarios. Based on the automated communication programs identified by this solution, risky behaviors such as fraud can be further identified, which helps improve communication security and safeguards various network application services.

[0118] To address the problems existing in the prior art, embodiments of this application also provide a device 70 for identifying automatic communication programs, such as... Figure 7 As shown, it includes:

[0119] The acquisition module 71 acquires the communication data of the communication program to be identified, the communication data including the time information of multiple sessions established by the communication program;

[0120] The determining module 72 determines the average session establishment interval duration in the communication data based on the time information of the multiple sessions;

[0121] Sampling module 73 samples the communication data based on the average session establishment interval duration to obtain the sampling result of the communication data, wherein the time length for sampling the communication data is greater than or equal to the sum of a preset number of the average session establishment interval durations;

[0122] If the deviation of the parameter values ​​of the session established by the communication program in the sampling result is less than a preset deviation, the identification module 74 determines that the communication program is an automatic communication program.

[0123] The apparatus provided in this application determines the sampling time based on the average session establishment interval, ensuring that the sampling results fully represent the communication behavior executed by the communication program, thereby effectively identifying whether the communication program is an automatic communication program. Furthermore, determining the sampling time based on the average session establishment interval improves identification efficiency and avoids excessively long sampling times that consume processing resources.

[0124] In this application, the modules in the apparatus provided can also implement the method steps provided in the method embodiments. Alternatively, the apparatus provided in this application may include other modules besides those described above to implement the method steps provided in the method embodiments. Furthermore, the apparatus provided in this application can achieve the technical effects achievable by the method embodiments.

[0125] Preferably, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described method embodiment for identifying an automatic communication program and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0126] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described method embodiment for identifying an automatic communication program, achieving the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0127] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0131] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0132] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0133] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0134] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for identifying automatic communication programs, characterized in that, include: Acquire communication data of the communication program to be identified, the communication data including time information of multiple sessions established by the communication program; The average session establishment interval in the communication data is determined based on the time information of the multiple sessions; The communication data is sampled based on the average session establishment interval to obtain the sampling result of the communication data, wherein the sampling time of the communication data is greater than or equal to the sum of a preset number of average session establishment intervals; If the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation, then the communication program is determined to be an automatic communication program. The parameter values ​​of the session established by the communication program include at least one of the following: the time interval between the establishment of adjacent sessions, the capacity of the data packets sent by the communication program in the session, the number of data packets sent by the communication program in the session, and the time interval between the transmission of adjacent data packets sent by the communication program in the session.

2. The method as described in claim 1, characterized in that, The communication data is sampled based on the average session establishment interval to obtain the sampling results of the communication data, including: The session pattern matching the communication data is determined based on the average session establishment interval. If the average session establishment interval is less than or equal to the preset interval, then the communication data is presampled using the preset sampling duration corresponding to the session mode to obtain the presampled result. The sampling duration for sampling the communication data is determined based on the number of sessions contained in the pre-sampling results; The communication data is sampled for the specified sampling duration to obtain the sampling result of the communication data.

3. The method as described in claim 2, characterized in that, The sampling duration for sampling the communication data is determined based on the number of sessions included in the pre-sampling results, including: If the number of sessions included in the pre-sampling result is less than or equal to the preset number, then the sum of the preset number of average session establishment intervals is determined as the sampling duration for the communication data sampling. If the number of sessions included in the pre-sampling result is greater than the preset number, the preset sampling duration is determined as the sampling duration for the communication data to be sampled.

4. The method as described in claim 3, characterized in that, If the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation, then the communication program is determined to be an automatic communication program, including: If the difference in the time interval between the establishment of adjacent sessions in the communication program established in the sampling results is less than the preset inter-session isolation difference, and The deviation in the capacity of data packets sent by the communication program in the session established by the communication program in the sampling results is less than the preset data packet capacity deviation, and The deviation in the number of data packets sent by the communication program in the session established by the communication program in the sampling results is less than the preset data packet number deviation. Then it is determined that the communication program is an automatic communication program.

5. The method as described in claim 2, characterized in that, The communication data is sampled based on the average session establishment interval to obtain the sampling results of the communication data, including: If the average session establishment interval is longer than the preset interval, the communication data is sampled for the preset sampling duration corresponding to the session mode to obtain the sampling result of the communication data. Wherein, if the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation, then the communication program is determined to be an automatic communication program, including: If the difference in the transmission time interval between adjacent data packets sent by the communication program in the session established by the communication program in the sampling result is less than the preset data packet isolation difference, then the communication program is determined to be an automatic communication program.

6. The method according to any one of claims 1 to 5, characterized in that, Before determining the average session establishment interval duration in the communication data based on the time information of the multiple sessions, the method further includes: Obtain the data information of each session in the communication data to obtain the metadata corresponding to each session. The metadata field information includes the session start time and at least one of the following: client identifier, server identifier, server port information, total number of bytes sent by the client, total number of bytes sent by the server, number of data packets sent by the client, and number of data packets sent by the server. Generate metadata logs based on the metadata corresponding to each session; The determination of the average session establishment interval in the communication data based on the time information of the multiple sessions includes: The average session establishment interval in the communication data is determined based on metadata including the session start time.

7. A device for identifying automatic communication programs, characterized in that, include: The acquisition module acquires the communication data of the communication program to be identified, the communication data including the time information of multiple sessions established by the communication program; The determining module determines the average session establishment interval duration in the communication data based on the time information of the multiple sessions; The sampling module samples the communication data based on the average session establishment interval duration to obtain the sampling result of the communication data, wherein the time length for sampling the communication data is greater than or equal to the sum of a preset number of the average session establishment interval durations; The identification module determines that the communication program is an automatic communication program if the deviation of the parameter values ​​of the session established by the communication program in the sampling results is less than a preset deviation. The parameter values ​​of the session established by the communication program include at least one of the following: the time interval between the establishment of adjacent sessions, the capacity of the data packets sent by the communication program in the session, the number of data packets sent by the communication program in the session, and the time interval between the transmission of adjacent data packets sent by the communication program in the session.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 6.

Citation Information

Patent Citations

  • System, method, and apparatus for inspecting online communication sessions via polymorphic security proxies

    EP2963887A1

  • Difference calculating device, difference calculating method, and difference calculating program

    WO2022024282A1