Method and system for identifying instant call service, and intelligent terminal

Abstract

The invention relates to a method and a system for identifying an instant call type service and an intelligent terminal, and relates to the field of network instant call technology, and the method comprises the following steps: obtaining an instant call data flow and participant information; identifying a call message and a message frame number; determining the content of the message; defining a common message content when the same message content exists between different call messages; determining a common number of common message contents; determining a common proportion based on the common number and the message frame number; defining the message content as key data when the common proportion is greater than the key critical proportion; screening instant call data streams with the same key data and marking the instant call data streams as the same call data stream; and analyzing the participant information corresponding to the same conversation data flow to obtain the same conversation participant. The method has the advantages that participants of the same session can be recognized by analyzing the same content without deeply analyzing specific content, and illegal behaviors of instant communication of illegal persons through a network can be detected.

Description

Technical Field

[0001] The present invention relates to the field of network instant messaging technology, and in particular to an identification method, system and intelligent terminal for instant messaging services. Background Art

[0002] Instant messaging services generally refer to real-time voice and video call functions and services achieved through the Internet or mobile networks.

[0003] In related technologies, a patent with Chinese patent number CN105656915A discloses an instant call method, which is executed by the calling side and the calling side is an Internet phone terminal. The method includes: initiating a multi-party voice call request to a signaling server, wherein the terminals designated to participate in the multi-party voice call in the multi-party voice call request include telephone terminals; establishing a data channel according to the remote access address returned by the signaling server in response to the multi-party voice call request; conducting the multi-party voice call after the designated terminal establishes the data channel according to the remote access address; during the establishment of the data channel of the terminal, the telephone terminal establishes the data channel corresponding to the remote access address through a gateway device. In addition, an instant call device and system matching this method are also provided. The above-mentioned instant call method, device, and system can realize intercommunication between Internet phone terminals and telephone terminals, and realize multi-party voice calls involving telephone terminals and Internet phone terminals.

[0004] Regarding the above-mentioned related technologies, at present, there are many instant call services and the extracted data streams are large, but each data stream only contains information about a single participant. It is difficult to extract and integrate which participants are making calls from a large number of data streams, which can easily be exploited by criminals to commit illegal acts through online instant calls. Summary of the Invention

[0005] In order to improve the problem that each data stream only contains information of a single participant, it is difficult to extract and integrate which participants are making calls from a large amount of data streams, and it is easy for criminals to use instant calls to commit illegal acts, the present invention provides an identification method, system and intelligent terminal for instant call services.

[0006] In a first aspect, the present invention provides a method for identifying instant call services, which adopts the following technical solution: A method for identifying instant call services, comprising: Get instant call data stream and participant information; Identify the instant call data stream based on preset message feature rules to obtain the call message and message frame number; Determining message content based on the call message; When the same message content exists between different call messages, the message content is defined as common message content; Determine the common quantity of common message content; Determine the common ratio based on the common quantity and the number of message frames; When the common ratio is greater than the preset critical ratio, the message content is defined as key data; Filtering instant call data streams with the same key data and identifying them as the same call data stream; Analyze the participant information corresponding to the same call data stream to obtain the same session participants.

[0007] By adopting the above technical solution, by analyzing the identical content of the messages in the data stream, there is no need to conduct in-depth analysis of the specific content. If the number of identical contents accounts for more than half, it is assumed to be a key feature. Then, based on the identical key features, the participants of the same conversation are identified. This helps operators to control the relevant data of online instant calls and detect illegal activities of criminals through online instant calls.

[0008] Optionally, the method of screening instant call data streams having the same key data and identifying them as the same call data stream includes: Create a temporary database; When the key data does not exist in the temporary database, the key data is stored in the temporary database, and a mapping relationship between the key data and the participant information is established; When key data exists in the temporary database, the mapping relationship corresponding to the key data is searched and the participant information is added to the mapping relationship; The instant call data stream of the key data is determined based on the mapping relationship and is identified as the same call data stream.

[0009] By adopting the above technical solution and establishing a temporary database, when a key data is generated, it can be matched in the database at any time, without having to wait until one key data is matched before starting to match another key data, thereby improving the efficiency of determining the same call data flow.

[0010] Optionally, a temporary database optimization method is also included, which includes: Select any key data in the temporary database and define it as existing key data; Determine data categories based on existing key data and preset classification rules; Determining existing data categories and corresponding attribution groups based on the temporary database; When the data category matches the existing data category, the existing key data is classified into the corresponding attribution group of the existing data category; When the data category does not match the existing data category, a new attribution group is established based on the data category, and the attribution group is defined as a new attribution group. The data category is matched with the existing data category and the new attribution group until all data categories match the existing data category.

[0011] By adopting the above technical solution, all key data will be classified and grouped in the database to facilitate searching by category, thereby improving the efficiency of matching key data in the temporary database.

[0012] Optionally, a method for determining whether to establish a new attribution relationship group based on the data category is further included, the method comprising: Determine the amount of existing key data based on the temporary database; When the amount of data exceeds a pre-set redundancy threshold, a new attribution group is created based on the data category; If the amount of data is less than the critical value, no creation is performed.

[0013] By adopting the above technical solution, when there is not much data, there is no need to establish an attribution relationship group, which reduces the steps of searching for the attribution relationship group and improves the efficiency of key data matching.

[0014] Optionally, a method for determining whether key data exists in the temporary database is also included, the method comprising: Determine the predicted data category based on key data and classification rules; Determine the number of categories based on the predicted data categories; When the number of categories is equal to 1, directly match the predicted data category with the existing data category; When the number of categories is greater than 1, the predicted data categories are sorted based on the preset key sorting rules, and the predicted data category with the highest sorting is defined as the priority data category; When the priority data category matches the existing data category, the corresponding attribution relationship group is defined as the priority attribution relationship group; Match key data with existing key data in the priority attribution group; When the key data matches the existing key data in the priority attribution relationship group, the existence judgment result of the key data in the temporary database is output; When the key data does not match the existing key data in the priority attribution group, the priority data category is updated based on the sorting until the key data matches the existing key data in the priority attribution group or all the predicted data categories cannot be matched; When all predicted data categories cannot be matched, a non-existence judgment result indicating that the key data does not exist in the temporary database is output.

[0015] By adopting the above technical solution, when there are multiple data categories, they are sorted according to the key sorting rules and then judged in sequence, thereby improving the efficiency of matching key data in the temporary database.

[0016] Optionally, a specific method for determining the common message content and common quantity is also included, and the method includes: Get the current call message; When there are identical message contents between adjacent call messages, one of the randomly selected message contents is defined as temporary message content, and the temporary quantity is accumulated; determining adjacent call messages based on the current call message when the temporary number is less than a preset ignore number threshold; Determine whether there is temporary message content in adjacent call messages; When temporary message content exists in adjacent call messages, the temporary quantity continues to be accumulated and the adjacent call messages continue to be updated; Re-determine the temporary message content and temporary quantity when the temporary message content does not exist in the adjacent call message; When temporary message content exists in adjacent call messages and the temporary quantity is greater than an ignored quantity threshold, the temporary message content is defined as common message content, and the temporary quantity is defined as a common quantity.

[0017] By adopting the above technical solution, continuous messages need to appear before they can become common message content, and it is not necessary to accumulate the content in each message all the time, which reduces the workload of the system and saves a lot of computing resources.

[0018] Optionally, when no temporary message content exists in the adjacent call message, the method for re-determining the temporary message content and the temporary quantity includes: When there is no temporary message content in the adjacent call message, the call message following the adjacent call message is defined as a subsequent call message; When temporary message contents are present in the subsequent call messages, the number of subsequent call messages is accumulated and defined as the estimated temporary number; Calculate the total provisional quantity based on the provisional quantity and the estimated provisional quantity; When the total temporary number is greater than the ignore number threshold, the adjacent call messages are considered to contain temporary message content and the temporary number is updated; When the total temporary number is less than the ignored number threshold, continue to determine subsequent call messages until the total temporary number is less than the ignored number threshold or there is no temporary message content in the subsequent call messages; When the total temporary quantity is less than the ignored quantity threshold and the temporary message content does not exist in the subsequent call message, the temporary message content and the temporary quantity are re-determined.

[0019] By adopting the above technical solution, when the subsequent content becomes continuous and the same, the middle message without the same content may have an interruption signal, so it can be ignored or regarded as a message with the same content, and the number of statistics is increased by one, thereby improving the accuracy of data accumulation.

[0020] Optionally, a subsequent method is further included when the temporary message content does not exist in the subsequent call message, the method comprising: When the subsequent call message does not contain temporary message content, the subsequent call message is defined as an adjacent call message, and the number of adjacent call messages that do not contain temporary message content is accumulated and defined as the abnormal temporary number; When the number of abnormal temporary messages exceeds the preset interruption threshold, the temporary message content and temporary number are directly re-determined; When the abnormal temporary number is less than the interruption threshold, the subsequent call message is determined based on the adjacent call message and whether the subsequent call message contains temporary message content.

[0021] By adopting the above technical solution, although a short interruption can be ignored, an interruption that lasts for a long time is regarded as another conversation and cannot be ignored.

[0022] In a second aspect, the present invention provides an instant call service identification system, which adopts the following technical solution: An instant call service identification system, comprising: The acquisition module is used to obtain the instant call data stream and participant information; A memory for storing a program for controlling the method for identifying the instant call service as described above; The processor loads and executes the program in the memory.

[0023] By adopting the above technical solution, by analyzing the identical content of the messages in the data stream, there is no need to conduct in-depth analysis of the specific content. If the number of identical contents accounts for more than half, it is assumed to be a key feature. Then, based on the identical key features, the participants of the same conversation are identified. This helps operators to control the relevant data of online instant calls and detect illegal activities of criminals through online instant calls.

[0024] In a third aspect, the present invention provides an intelligent terminal, which adopts the following technical solution: An intelligent terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any one of the methods described above.

[0025] By adopting the above technical solution, by analyzing the identical content of the messages in the data stream, there is no need to conduct in-depth analysis of the specific content. If the number of identical contents accounts for more than half, it is assumed to be a key feature. Then, based on the identical key features, the participants of the same conversation are identified. This helps operators to control the relevant data of online instant calls and detect illegal activities of criminals through online instant calls.

[0026] In summary, the present invention includes at least one of the following beneficial technical effects: 1. By analyzing the identical content of messages in the data stream, participants in the same conversation can be identified without in-depth analysis of the specific content. This helps operators control the relevant data of online instant calls and detect illegal activities of illegal personnel through online instant calls. 2. By establishing a temporary database, when a key data is generated, it can be matched in the database at any time, without having to wait until one key data is matched before starting to match another key data, thus improving the efficiency of determining the same call data flow; 3. Only when all consecutive messages appear can they become common message content. It is not necessary to accumulate the content in each message all the time, which reduces the workload of the system and saves a lot of computing resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a method for identifying instant call services in an embodiment of the present application.

[0028] Figure 2 This is a flowchart of a method for screening instant call data streams having the same key data and identifying them as the same call data stream in an embodiment of the present application.

[0029] Figure 3 It is a flowchart of the optimization method of the temporary database in an embodiment of the present application.

[0030] Figure 4 This is a flowchart of a method for determining whether to establish a new attribution relationship group based on data category in an embodiment of the present application.

[0031] Figure 5 This is a flowchart of a method for determining whether there is key data in a temporary database in an embodiment of the present application.

[0032] Figure 6 It is a flowchart of a specific method for determining common message content and common quantity in an embodiment of the present application.

[0033] Figure 7 It is a flowchart of a method for redetermining temporary message content and temporary quantity when there is no temporary message content in adjacent call messages in an embodiment of the present application.

[0034] Figure 8 This is a flowchart of a subsequent method when there is no temporary message content in a subsequent call message in an embodiment of the present application.

[0035] Figure 9 This is a module diagram of a method for identifying instant messaging services in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0037] The embodiment of the present invention discloses a method for identifying instant call services. Figure 1 , a method for identifying instant call services includes: Step 100: Obtain instant call data stream and participant information.

[0038] An instant call data stream refers to the collection of audio and video data transmitted over the network within an instant messaging application (such as a voice call or video call). It is a sequential collection of bytes with a start and end point, used to transmit call data. Participant information refers to the information of the participants in the instant call data stream. This information can be obtained using the IP address of the device hardware or by logging into the third-party software that sends the instant call data stream using the account and password.

[0039] Step 101: Identify the instant call data stream based on preset message feature rules to obtain the call message and message frame number.

[0040] Message feature rules are rules for identifying messages in a specific message format. Once identified using these message feature rules, there's no need to decipher the specific content of the message, and thus no need to decrypt the message. Message feature rules can be used to identify messages based on quantifiable features, such as rules analyzing message structure (identification fields in fixed locations), behavior (frequency of message transmission), and contextual features (correlation with previous and subsequent messages, such as sequence number continuity). Call messages are part of an instant call data stream and are the basic data unit transmitted in network communications. Identification is performed using message feature rules. The number of message frames represents the number of call messages.

[0041] The message feature rules here analyze the message structure, for example, by extracting characteristic fields. Common characteristic fields include the server IP and port, UA (User Agent), Host, URI (Uniform Resource Identifier), Refer_URI (Referring URI), and SNI (Server Name Indication). By extracting these fields, message classification, monitoring, security detection, and optimization can be achieved.

[0042] Since most messages are encrypted, the detailed meaning of the fields is unknown. Deeply deciphering the message content would require a significant amount of computer work. Therefore, we employ special message feature rules for simple recognition, eliminating the need to know the detailed content and significantly reducing the workload.

[0043] Step 102: Determine the message content based on the call message.

[0044] The message content is the actual data in the message payload area. Its format and meaning depend on the specific protocol and application scenario. Message content can be text, binary data, control instructions, multimedia data, etc. The detailed content is not required here; only the encrypted content is required. The determination method is direct reading.

[0045] Step 103: When the same message content exists between different call messages, the message content is defined as common message content.

[0046] If the same message content exists between different call messages, it means that the encrypted content of the two is the same, and the content before encryption is also the same. The judgment method is to directly judge the surface without decryption.

[0047] Step 104: Determine the common quantity of common message contents.

[0048] The common number is the number of common message contents. The method of determining here is cumulative counting, that is, if a common message content appears, it is recorded as 1, and then continuously accumulated.

[0049] Step 105: Determine the common ratio based on the common quantity and the number of message frames.

[0050] The common ratio is the percentage of packets with common content among all packets. It is calculated by dividing the common number by the number of packet frames.

[0051] Step 106: When the common ratio is greater than a preset critical ratio, the common message content is defined as key data.

[0052] The critical percentage is the percentage above which it can be basically determined to be the same conversation, for example: 50%. Professionals in this field obtain the corresponding public data and publicly available decryption methods from the telecommunications company to decrypt the same conversation, and then extract the corresponding common message content and the corresponding common percentage. Finally, when the common percentage exceeds this value, the common message content is the key data, and when it does not exceed this value, it does not meet the key data requirements, thus determining the boundary value. When the common percentage is greater than the critical percentage, it means that the call message at this time is highly likely to be the same conversation. In this case, the common message content is defined as the key data to determine whether it is the same conversation.

[0053] Step 107: Screen the instant call data streams with the same key data and mark them as the same call data stream.

[0054] The same call data stream is different instant call data streams in the same call.

[0055] When all of them have key data, it is highly likely that they are in the same conversation. Therefore, in order to determine all participants in this conversation, it is necessary to filter out all instant call data streams with key data.

[0056] Step 108: Analyze the participant information corresponding to the same call data stream to obtain the same session participants.

[0057] Reference Figure 2 The method of filtering instant call data streams with the same key data and identifying them as the same call data stream includes: Step 200: Create a temporary database.

[0058] A temporary database is a database that is created temporarily. It is used to store key data and participant information and is deleted when the session ends.

[0059] Step 201: When the key data does not exist in the temporary database, the key data is stored in the temporary database, and a mapping relationship between the key data and the participant information is established.

[0060] A mapping relationship describes the correspondence between two or more entities. That is, once a mapping relationship is established, any information can be found from another information. If it does not exist, it means that the key data does not exist in the database at this time, and the corresponding participant information does not exist, so it needs to be added.

[0061] Step 202: When the key data exists in the temporary database, the mapping relationship corresponding to the key data is searched and the participant information is added to the mapping relationship.

[0062] When key data exists in the temporary database, it means that there is a corresponding mapping relationship in the temporary database. At this time, it contains different participant information for the same key data, which makes it convenient to filter.

[0063] Step 203: Determine the instant call data stream of the key data based on the mapping relationship and identify them as the same call data stream.

[0064] Once the mapping relationship is known, the same call data flow is also known. By establishing a temporary database, when a key data is generated, it can be matched in the database at any time, without having to wait until one key data is matched before starting to match another key data, which improves the efficiency of determining the same call data flow.

[0065] Reference Figure 3 , further comprising an optimization method for a temporary database, the method comprising: Step 300: arbitrarily select a key data in a temporary database and define the key data as existing key data.

[0066] Step 301: Determine the data category based on existing key data and preset classification rules.

[0067] The classification rule is a rule set by humans, and here the rule can be used to classify the structure of the encrypted data. The data category is the category of the existing key data after the classification rule is passed.

[0068] Step 302: Determine existing data categories and corresponding attribution relationship groups based on the temporary database.

[0069] The determination method is direct search. The existing key data in the internal belonging relationship group are all combinations of the same existing data category.

[0070] Step 303: When the data category matches the existing data category, the existing key data is assigned to the affiliation group corresponding to the existing data category.

[0071] When the data category matches the existing data category, it means that the data category belongs to the attribution group, and the data category can be classified into the attribution group.

[0072] Step 304: When the data category does not match the existing data category, a new attribution group is established based on the data category, the attribution group is defined as a new attribution group, and the data category is matched with the existing data category and the new attribution group until all data categories match the existing data category.

[0073] When the data category does not match the existing data category, it means that there is no match at this time and there is no corresponding attribution group. For convenience, a new attribution group is created.

[0074] The purpose of steps 300-304 here is to classify all data. When new key data comes in, the corresponding attribution group can be found according to its own category, which greatly reduces the tediousness of matching all existing key data.

[0075] Reference Figure 4 , further comprising a method for determining whether to establish a new attribution relationship group based on the data category, the method comprising: Step 400: Determine the amount of existing key data based on the temporary database.

[0076] The data quantity is the number of existing key data, which is determined by counting the number of existing keys in the temporary database.

[0077] Step 401: When the data quantity is greater than a preset complexity threshold, a new attribution group is created based on the data category.

[0078] If the critical number of tediousness exceeds this number, the default is set to the critical number of tedious matching. This is determined by personnel in this field based on the length of time it takes for the computer to obtain matching results during actual experiments. If it is greater than this number, it indicates that the number is large and the matching is tedious, so it is possible to establish an affiliation group to reduce the workload.

[0079] Step 402: Do not create when the data quantity is less than the cumbersome threshold.

[0080] When the amount of data is less than the critical value of complexity, it means that the workload of one-to-one matching is less than that of group matching, so one-to-one matching can be performed without establishing an affiliation group.

[0081] At this time, the affiliation group may not be established when the first key data is processed.

[0082] Reference Figure 5 , and also includes a method for determining whether key data exists in the temporary database, the method comprising: Step 500: Determine the predicted data category based on key data and classification rules.

[0083] The predicted data category is the category of key data that has not yet entered the temporary database and become the existing key data. The determination method is similar to step 301 and will not be repeated here.

[0084] Step 501: Determine the number of categories based on the predicted data categories.

[0085] The number of categories is the number of predicted data categories included in the key data, determined by counting.

[0086] Step 502: When the number of categories is equal to 1, directly match the predicted data category with the existing data category.

[0087] When the number of categories is equal to 1, it means that there is only one predicted data category. In this case, there is no need to select the predicted data category and you can match it directly.

[0088] Step 503 : When the number of categories is greater than 1, the predicted data categories are sorted based on a preset key sorting rule, and the predicted data category with the highest sorting level is defined as the priority data category.

[0089] The key sorting rule is that whichever data category is key is sorted ahead of the less key data categories. The definition of key here can be set manually and expressed in the form of a numerical value.

[0090] Step 504: When the priority data category matches the existing data category, define the corresponding attribution relationship group as the priority attribution relationship group.

[0091] The matching between the priority data category and the existing data category indicates that the match is successful at this time, and the key data can be matched with the existing key data in the priority key group.

[0092] Step 505: Match the key data with the existing key data in the priority attribution group.

[0093] Step 506: When the key data matches the existing key data in the priority belonging relationship group, output the existence determination result of the key data in the temporary database.

[0094] The existence judgment result is the result that the key data exists in the temporary database. The output method is to execute step 202.

[0095] When the key data matches the existing key data in the priority attribution relationship group, it indicates that the key data exists in the database, and an existence judgment result is output, ie, step 202 is executed.

[0096] Step 507: When the key data does not match the existing key data in the priority attribution relationship group, the priority data category is updated based on the sorting until the key data matches the existing key data in the priority attribution relationship group or all the predicted data categories cannot be matched.

[0097] If the key data does not match the existing key data in the priority attribution group, it means that the key data cannot be found in the priority attribution group at this time, but it does not rule out finding it in other attribution groups. Therefore, the next data category and priority attribution group are determined and then matched.

[0098] Step 508: When all the predicted data categories cannot be matched, output a non-existence judgment result that the key data does not exist in the temporary database.

[0099] The non-existence judgment result is a result that the key data does not exist in the temporary database. The output method is to execute step 201.

[0100] When all the predicted data categories cannot be matched, it means that the key data has been matched with all the existing key data that may be successfully matched in the temporary database and all the matches have failed, then the output is a non-existent judgment result, and step 201 is executed.

[0101] Reference Figure 6 , further comprising a specific method for determining the common message content and common quantity, the method comprising: Step 600: Obtain the current call message.

[0102] The current call message is the currently selected call message. You can select any method to obtain it.

[0103] Step 601: When there are identical message contents between adjacent call messages, one of the message contents is randomly selected and defined as temporary message content, and the temporary quantity is accumulated.

[0104] The temporary number is the number of temporary messages with the same content. If the next call message contains the same content, the number is incremented by 1. To determine whether to continue incrementing, the corresponding message content is temporarily defined as temporary.

[0105] Here, there are multiple contents of the temporary message content, and one is selected at random.

[0106] Step 602: Determine adjacent call messages based on the current call message when the temporary number is less than a preset ignore number threshold.

[0107] The ignore threshold is used to disregard temporary messages. Temporary message content does not need to be matched against the temporary database; instead, the temporary quantity corresponding to the temporary message content needs to be accumulated. When the temporary quantity is less than the ignore threshold, it indicates that the temporary message content can be ignored and no matching is performed against the temporary database. However, to accumulate the temporary quantity, it is necessary to continue determining adjacent call messages.

[0108] Step 603: Determine whether there is any temporary message content in the adjacent call message.

[0109] What is judged here is whether the same temporary message content exists.

[0110] Step 604: When the temporary message content exists in the adjacent call message, the temporary number is continued to be accumulated, and the adjacent call message is continued to be updated.

[0111] Step 605: When the temporary message content does not exist in the adjacent call message, the temporary message content and the temporary quantity are re-determined.

[0112] Here, if the temporary message content does not exist in the adjacent call message, it means that the temporary message content selected in step 601 does not meet the requirements, and then steps 601-603 are re-executed, that is, a temporary message content is re-selected for statistics.

[0113] Step 606: When temporary message contents exist in adjacent call messages and the temporary quantity is greater than the ignore quantity threshold, define the temporary message contents as common message contents and define the temporary quantity as a common quantity.

[0114] When temporary message contents exist in adjacent call messages and the temporary quantity is greater than the ignore quantity threshold, the temporary quantity and temporary message contents have meaning and can be output as the common quantity and message contents respectively.

[0115] Reference Figure 7 The method for re-determining the temporary message content and the temporary quantity when the temporary message content does not exist in the adjacent call message includes: Step 700: When there is no temporary message content in the adjacent call message, define the call message following the adjacent call message as a subsequent call message.

[0116] If the adjacent call message contains no temporary message content, the call being analyzed may have been disconnected. This can be caused by signal interference or by the user hanging up and ending the call. Subsequent call messages are those that follow and are adjacent to the adjacent call message.

[0117] Step 701: When temporary message contents exist in subsequent call messages, the number of subsequent call messages is accumulated and defined as an estimated temporary number.

[0118] When accumulating the estimated temporary quantity here, the temporary message content must also be continuously present in the subsequent call messages. If the temporary message content exists in the subsequent call message, it means that the temporary message content that no longer exists in the previous process exists again in the subsequent process, so it is necessary to determine the reason for the absence of the temporary message content in the middle.

[0119] Step 702: Calculate the total temporary quantity based on the temporary quantity and the expected temporary quantity.

[0120] The total provisional quantity is the sum of the provisional quantity and the estimated provisional quantity. It is calculated by adding the two.

[0121] Step 703: When the total temporary number is greater than the ignore number threshold, the adjacent call messages are regarded as containing temporary message content, and the temporary number is updated.

[0122] When the total temporary count exceeds the ignore threshold, attention should be paid to this situation, as it is suspected to be critical data. Adjacent call messages without temporary content may be due to abnormal data collection or system equipment issues, so they should be considered to contain temporary content and the number of these adjacent call messages should also be counted in the temporary count.

[0123] Step 704: When the total temporary number is less than the ignored number threshold, continue to determine subsequent call messages until the total temporary number is less than the ignored number threshold or there is no temporary message content in the subsequent call messages.

[0124] When the total temporary number is less than the ignore number threshold, it indicates that the detection has not been completed or the total temporary number can be ignored, but it is not possible to determine which one it is, and then continue to determine the subsequent call message and execute steps 700-704.

[0125] Step 705: When the total temporary quantity is less than the ignored quantity threshold and there is no temporary message content in the subsequent call message, the temporary message content and the temporary quantity are re-determined.

[0126] If the temporary message content does not exist in the subsequent call message, it means that the call has been interrupted again. In this case, the reason for the interruption is the message itself, that is, it is not critical data, so the temporary message content and temporary quantity are re-determined.

[0127] Reference Figure 8 , further comprising a subsequent method when the temporary message content does not exist in the subsequent call message, the method comprising: Step 800: When the subsequent call message does not contain temporary message content, the subsequent call message is defined as an adjacent call message, and the number of adjacent call messages without temporary message content is accumulated and defined as an abnormal temporary number.

[0128] The purpose of defining subsequent call messages as adjacent call messages here is to determine the number of call messages without the same temporary message content in between.

[0129] Step 801: When the abnormal temporary quantity is greater than the preset interruption threshold, the temporary message content and the temporary quantity are directly re-determined.

[0130] The interruption threshold is a manually set number of adjacent call messages that can be interrupted. This value was determined by analyzing extensive experimental data and segmenting cases where the number of abnormalities exceeds this threshold. If the number of abnormal temporary messages exceeds the interruption threshold, it indicates that the problem is not due to the system but to critical data, so the temporary message content and number can be simply redefined.

[0131] Step 802: When the number of temporary abnormalities is less than the interruption threshold, continue to determine subsequent call messages based on adjacent call messages and continue to determine whether there is temporary message content in the subsequent call message.

[0132] When the number of temporary abnormalities is less than the interruption threshold, it means that it is still impossible to determine whether it is a system problem at this time, and then continue to determine whether there is temporary message content in the subsequent call message. If so, follow steps 700-705. If not, follow steps 800-801.

[0133] Based on the same inventive concept, an embodiment of the present invention provides an identification system for instant call services.

[0134] Reference Figure 9 , an identification system for instant call services, comprising: The acquisition module is used to obtain the instant call data stream and participant information; A memory for storing a program for controlling a method for identifying an instant call service; The processor loads and executes the program in the memory.

[0135] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes a method for identifying instant call services.

[0136] Those skilled in the art will clearly understand that for the sake of convenience and brevity, the division of the above-mentioned functional modules is only used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the above-mentioned systems, devices, and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0137] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A method for identifying instant call services, characterized in that: include: Get instant call data stream and participant information; Identify the instant call data stream based on preset message feature rules to obtain the call message and message frame number; Determining message content based on the call message; When the same message content exists between different call messages, the message content is defined as common message content; Determine the common quantity of common message content; Determine the common ratio based on the common quantity and the number of message frames; When the common ratio is greater than a preset critical ratio, the common message content is defined as key data; Filtering instant call data streams with the same key data and identifying them as the same call data stream; Analyze the participant information corresponding to the same call data stream to obtain the same session participants.

2. The method for identifying instant call services according to claim 1, wherein: Methods for filtering instant call data streams having the same key data and identifying them as the same call data stream include: Create a temporary database; When the key data does not exist in the temporary database, the key data is stored in the temporary database, and a mapping relationship between the key data and the participant information is established; When key data exists in the temporary database, the mapping relationship corresponding to the key data is searched and the participant information is added to the mapping relationship; The instant call data stream of the key data is determined based on the mapping relationship and is identified as the same call data stream.

3. The method for identifying instant call services according to claim 2, wherein: The invention also includes a temporary database optimization method, which includes: Select any key data in the temporary database and define it as existing key data; Determine data categories based on existing key data and preset classification rules; Determining existing data categories and corresponding attribution groups based on the temporary database; When the data category matches the existing data category, the existing key data is classified into the corresponding attribution group of the existing data category; When the data category does not match the existing data category, a new attribution group is established based on the data category, and the attribution group is defined as a new attribution group. The data category is matched with the existing data category and the new attribution group until all data categories match the existing data category.

4. The method for identifying instant call services according to claim 3, wherein: The method also includes a method for determining whether to establish a new attribution relationship group based on the data category, the method comprising: Determine the amount of existing key data based on the temporary database; When the amount of data exceeds a pre-set redundancy threshold, a new attribution group is created based on the data category; If the amount of data is less than the critical value, no creation is performed.

5. The method for identifying instant call services according to claim 3, wherein: The invention also includes a method for determining whether key data exists in the temporary database, the method comprising: Determine the predicted data category based on key data and classification rules; Determine the number of categories based on the predicted data categories; When the number of categories is equal to 1, directly match the predicted data category with the existing data category; When the number of categories is greater than 1, the predicted data categories are sorted based on the preset key sorting rules, and the predicted data category with the highest sorting is defined as the priority data category; When the priority data category matches the existing data category, the corresponding attribution relationship group is defined as the priority attribution relationship group; Match key data with existing key data in the priority attribution group; When the key data matches the existing key data in the priority attribution relationship group, the existence judgment result of the key data in the temporary database is output; When the key data does not match the existing key data in the priority attribution group, the priority data category is updated based on the sorting until the key data matches the existing key data in the priority attribution group or all the predicted data categories cannot be matched; When all predicted data categories cannot be matched, a non-existence judgment result indicating that the key data does not exist in the temporary database is output.

6. The method for identifying instant call services according to claim 1, wherein: The method also includes a specific method for determining the common message content and common quantity, the method comprising: Get the current call message; When there are identical message contents between adjacent call messages, one of the randomly selected message contents is defined as temporary message content, and the temporary quantity is accumulated; determining adjacent call messages based on the current call message when the temporary number is less than a preset ignore number threshold; Determine whether there is temporary message content in adjacent call messages; When temporary message content exists in adjacent call messages, the temporary quantity continues to be accumulated and the adjacent call messages continue to be updated; Re-determine the temporary message content and temporary quantity when the temporary message content does not exist in the adjacent call message; When temporary message content exists in adjacent call messages and the temporary quantity is greater than an ignored quantity threshold, the temporary message content is defined as common message content, and the temporary quantity is defined as a common quantity.

7. The method for identifying instant call services according to claim 6, wherein: The method for re-determining the temporary message content and the temporary quantity when the temporary message content does not exist in the adjacent call message includes: When there is no temporary message content in the adjacent call message, the call message following the adjacent call message is defined as a subsequent call message; When temporary message contents are present in the subsequent call messages, the number of subsequent call messages is accumulated and defined as the estimated temporary number; Calculate the total provisional quantity based on the provisional quantity and the estimated provisional quantity; When the total temporary number is greater than the ignore number threshold, the adjacent call messages are considered to contain temporary message content and the temporary number is updated; When the total temporary number is less than the ignored number threshold, continue to determine subsequent call messages until the total temporary number is less than the ignored number threshold or there is no temporary message content in the subsequent call messages; When the total temporary quantity is less than the ignored quantity threshold and the temporary message content does not exist in the subsequent call message, the temporary message content and the temporary quantity are re-determined.

8. The method for identifying instant call services according to claim 7, wherein: Also included is a subsequent method when the temporary message content does not exist in the subsequent call message, the method comprising: When the subsequent call message does not contain temporary message content, the subsequent call message is defined as an adjacent call message, and the number of adjacent call messages that do not contain temporary message content is accumulated and defined as the abnormal temporary number; When the number of abnormal temporary messages exceeds the preset interruption threshold, the temporary message content and temporary number are directly re-determined; When the abnormal temporary number is less than the interruption threshold, the subsequent call message is determined based on the adjacent call message and whether the subsequent call message contains temporary message content.

9. An identification system for instant call services, characterized in that: include: The acquisition module is used to obtain the instant call data stream and participant information; A memory for storing a program of a control method for an instant call service identification method according to any one of claims 1 to 8; The processor loads and executes the program in the memory.

10. An intelligent terminal, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executes the method according to any one of claims 1 to 8.

Images