# US 2011/0047269 A1 · Device, method and system for detecting unwanted conversational media session > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2011/0047269 A1 - Document ID: US20110047269A1 - Status: Published application - Kind: A1 - Application number: 12/938,191 - Filed: 2010-11-02 - Published: 2011-02-24 - Earliest claimed: 2006-09-21 - Assignees: Commtouch Software Ltd. - Inventors: Aharon SATT; Amir Lev - Web page: https://patentgrep.com/patent/US20110047269A1 ## CPC - G10L 15/20: Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech (G10L21/02 takes precedence) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Some embodiments of the invention relate to a method and a system for detecting unwanted conversational media session data. In accordance with one aspect of the invention, a method of detecting unwanted conversation media session data according to some embodiments of the invention may include calculating two or more progressive similarity scores each with respect to a different instant during a progress of a real-time conversational media session, wherein each of said scores is associated with a similarity between the conversational media session's media data that was available at the associated instant and a reference data item corresponding to media data of a previous conversational media session, and evaluating progressive similarity between the real-time conversational media session and the reference data item based upon the two or more progressive similarity scores. ## Claims ### Claim 1 A method of detecting unwanted conversational media session data, said method comprising: calculating two or more progressive similarity scores each with respect to a different instant during a progress of a real-time conversational media session (hereinafter: “CMS”), wherein each of said scores is associated with a similarity between the CMS's media data that was available at the associated instant and a reference data item corresponding to media data of a previous CMS; and evaluating progressive similarity between the real-time CMS and the reference data item based upon the two or more progressive similarity scores. ### Claim 2 (depends on 1) The method according to claim 1, wherein said calculating is performed on-the-fly during the progress of the real-time CMS. ### Claim 3 (depends on 2) The method according to claim 2, wherein each of said similarity scores is sensitive to the amount of the extent of media data available at the instant with which the score is associated. ### Claim 4 (depends on 1) The method according to claim 1, wherein said reference data item includes one or more of the following: a. a recording of a previous CMS or of a portion of a previous CMS; b. a signature of a previous CMS or of a portion of a previous CMS; c. a schematic representation providing progression schemes of one or more components of the previous CMS or of a portion of a previous CMS. ### Claim 5 (depends on 1) The method according to claim 1, wherein said calculating comprises: calculating a first similarity score with respect to a first amount of media data available at a first instant during the progress of the real-time CMS; and calculating a second similarity score with respect to a second amount of media data available at a second instant during the progress of the real-time CMS, wherein said second instant succeeds said first instant. ### Claim 6 (depends on 5) The method according to claim 5, wherein said second amount of media data includes the first amount of media data and the media data received between said first and second instants. ### Claim 7 (depends on 5) The method according to claim 5, wherein said second amount of media data includes the media data received between said first and second instants. ### Claim 8 (depends on 1) The method according to claim 1, wherein said evaluating comprises implementing a unwanted CMS detection criteria, said CMS detection criteria being associated with at least a progressive similarity criterion, and wherein the progressive similarity criterion is usable for determining based upon two or more progressive similarity scores whether the real-time CMS and the reference data item are similar. ### Claim 9 (depends on 8) The method according to claim 8, wherein in accordance with the unwanted CMS detection criteria a unwanted real-time CMS is a real-time CMS which complies with at least one progressive similarity criterion. ### Claim 10 (depends on 8) The method according to claim 8, wherein the unwanted CMS detection criteria further includes a progressive dissimilarity criterion, and wherein the progressive dissimilarity criterion is usable for determining based upon one or more progressive similarity scores whether the real-time CMS and the reference data item are dissimilar. ### Claim 11 (depends on 9) The method according to claim 9, wherein the progressive similarity criterion includes a progressive similarity threshold and wherein said evaluating includes implementing the progressive similarity threshold for determining whether a progressive similarity score(s) is indicative of similarity between the real-time CMS and the reference data item. ### Claim 12 (depends on 10) The method according to claim 10, wherein the progressive similarity criterion includes a progressive dissimilarity threshold usable for determining whether a progressive similarity score(s) is indicative of dissimilarity between the real-time CMS and the reference data item. ### Claim 13 (depends on 12) The method according to claim 12, wherein said evaluating comprises determining based upon the two or more progressive similarity scores whether the real-time CMS and the reference data item are similar, dissimilar or that further progressive similarity scores are necessary to determine similarity or dissimilarity. ### Claim 14 (depends on 9) The method according to claim 9, wherein said calculating is an iterative process and as part of each iteration thereof a progressive similarity score is calculated, and wherein said calculating is continued until enough real-time CMS data is available to determine in accordance with the unwanted CMS criteria whether the real-time CMS is unwanted. ### Claim 15 (depends on 14) The method according to claim 14, wherein in accordance with the unwanted CMS detection criteria the amount of data real-time CMS data required to determine that the real-time CMS is unwanted is associated with at least one or more progressive similarity scores calculated for the real-time CMS and a reference data item. ### Claim 16 (depends on 8) The method according to claim 8, wherein said unwanted CMS detection criteria is further associated with a CMS traffic control rule, and wherein the CMS traffic control rule is usable for adjusting the progressive similarity criterion based upon the signaling data associated with the real-time CMS. ### Claim 17 (depends on 16) The method according to claim 16, wherein adjusting the progressive similarity criterion comprises identifying an originator of the real-time CMS and adjusting the progressive similarity criterion if it is determined the real-time CMS is associated with a certain originator or with a certain group of originators. ### Claim 18 (depends on 16) The method according to claim 16, further comprising generating a CMS traffic control rule based upon real-time CMS's signaling data in case it is determined that the real-time CMS is similar to one or more reference data items. ### Claim 19 (depends on 98) The method according to claim 98, further comprising discontinuing the real-time CMS once it is established that the real-time CMS complies with the unwanted CMS detection criterion. ### Claim 20 (depends on 9) The method according to claim 9, further comprising blocking the real-time CMS upon establishing that the real-time CMS complies with the unwanted CMS detection criterion and before the real-time CMS is initiated at its intended recipient. ### Claim 21 (depends on 8) The method according to claim 8, wherein the unwanted CMS detection criteria includes one or more tolerance values, said tolerance values being configured to accommodate for one or more of the following: expected packet loss over the network, constant delay between MSCs and delay variation or jitter between MSCs. ### Claim 22 (depends on 1) The method according to claim 1, further comprising utilizing an intermediary CMS monitoring unit to intercept real-time CMS data traversing the network, wherein said calculating and evaluating is performed in respect of the intercepted real-time CMS and a previously intercepted CMS. ### Claim 23 (depends on 22) The method according to claim 22, wherein said intermediary CMS monitoring unit is utilized in a manner to enable the interception of real-time CMS data from nonspecific originators and/or to enable the interception of real-time CMS data traversing the network towards nonspecific recipients. ### Claim 24 (depends on 1) The method according to claim 1, further comprising providing a plurality of reference data items for a real-time CMS and performing said calculating and evaluating in respect of each of the plurality of reference data items. ### Claim 25 A system for detecting unwanted conversational media sessions, said system comprising: a reference database including one or more reference data items, each reference data item corresponding to media data of a previous CMS; and a progressive similarity evaluation module (hereinafter: “PSE module”), said PSE module being adapted to calculate two or more progressive similarity scores each with respect to a different instant during a progress of a real-time CMS, wherein each of said scores is associated with a similarity between the CMS's media data that was available at the associated instant and a reference data item, and said PSE module being further adapted to evaluate progressive similarity between the real-time CMS and the reference data item based upon the two or more progressive similarity scores. ### Claim 26 (depends on 25) The system according to claim 25, wherein at least said PSE module is associated with an intended recipient of the real-time CMS. ### Claim 27 (depends on 25) The system according to claim 25, wherein at least said PSE module is associated with a CMS monitoring node, said CMS monitoring node including an interception module for enabling the CMS monitoring node to intercept real-time CMS data from nonspecific originators and/or to intercept real-time CMS data traversing the network towards nonspecific recipients. ### Claim 28 (depends on 27) The system according to claim 27, wherein said CMS monitoring node further comprises a CMS media simulator, said CMS media simulator being adapted to generate real-time CMS media data in response to real-time CMS data intercepted by the interception module.