Communication data analysis method

Abstract

A communication data analysis method is provided that can analyze the level of relationships between multiple users. [Solution] In the server 3, as a communication data analysis method, an acquisition process (STEP 1) is executed to acquire multiple types of communication data communicated between a first user M1 and a second user M2 via multiple types of communication services, and a relationship level analysis process (STEP 12) is executed to estimate a relationship level representing the level of the relationship between the first user M1 and the second user M2 using a machine learning model based on the order of the communication data sent from the first user M1 to the second user M2 and the type of communication service in the communication data.

Description

[Technical Field]

[0001] The present invention relates to a communication data analysis method for analyzing a plurality of types of communication data in a plurality of types of communication services. [Background technology]

[0002] A conventional analysis method for analyzing communication data in a communication service is disclosed in Patent Document 1. In this analysis method, communication data between multiple terminals stored in multiple terminals is analyzed to evaluate the relevance of the data to a predetermined event (hereinafter referred to as a "predetermined event"). Specifically, the relevance is evaluated based on the number of times information related to the predetermined event appears in the communication data, the frequency of appearance, or the importance of the information. Then, based on the evaluation results, the relationships between users of the multiple terminals are displayed on a monitor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-62098 Summary of the Invention [Problem to be solved by the invention]

[0004] According to the above-mentioned conventional analysis method, although it is possible to analyze the degree of relevance of communication data to a specified incident, there is a problem in that it is not possible to analyze the level of relationship (e.g., intimacy) between multiple users regardless of the specified incident.

[0005] The present invention has been made to solve the above-mentioned problems, and has an object to provide a communication data analysis method that can analyze the level of relationships between multiple users. [Means for solving the problem]

[0006] In order to achieve the above object, the invention of claim 1 is a communication data analysis method for analyzing, by a processing device, a plurality of types of communication data communicated between a first user and a second user via a plurality of types of communication services, the processing device including: an acquisition step of acquiring the plurality of types of communication data; and an acquisition step of acquiring the plurality of types of communication data, the plurality of types of communication data communicated between the first user and the second user, the order and communication time of the communication data. occurrence an analyzing step of performing an analyzing process to estimate a relationship level representing a level of a relationship between the first user and the second user using a machine learning model based on at least one of the date and time and the type of communication service in the communication data; The machine learning model is a model that learns the correlation between at least one of the order and the date and time of communication of a predetermined number of communication data communicated between a pair of users, the type of communication service in the communication data, and the relationship level of one user to the other user, using as learning data the order and the date and time of communication, and the type, and the relationship level. It is characterized by the following.

[0007] According to this communication data analysis method, a processing device acquires multiple types of communication data communicated between a first user and a second user via multiple types of communication services. Of the multiple types of communication data acquired in this manner, at least one of the order of the communication data communicated between the first user and the second user and the date and time of communication occurrence, and the type of communication service in the communication data can be considered to represent the transition and level of the relationship between the first user and the second user.

[0008] Therefore, by estimating a relationship level representing the level of the relationship between the first user and the second user using a machine learning model based on at least one of the order and the date and time of communication occurrence, and the type of communication service in the communication data, the level of the relationship between the first user and the second user can be accurately estimated. Furthermore, if the first user and the second user have a business relationship, the level of the business relationship between the first user and the second user can be accurately estimated, allowing the second user to effectively utilize the estimation result in business. Note that in this specification, the "relationship between the first user and the second user" refers to the intimacy, closeness, and emotional distance between the first user and the second user. Furthermore, the "order of communication data" refers to the order of the timing (occurrence time) of the occurrence of the communication data.

[0009] In the present invention, it is preferable that the arithmetic processing device further executes a notifying step of notifying the second user of the estimation result of the relationship level.

[0010] According to this communication data analysis method, the estimation result of the relationship level is notified to the second user by executing the notifying step, so that the second user can know the objective determination result regarding the relationship level of the first user with the second user even if the second user is unable to appropriately determine the relationship with the first user by himself / herself.

[0011] In the present invention, it is preferable that the processing device further executes a suggestion step for suggesting to the second user, based on the relationship level, the use of at least one of a plurality of types of communication services as a communication means when the second user contacts the first user.

[0012] According to this communication data analysis method, by executing the proposing step, the second user is proposed to use at least one of a plurality of communication services as a communication means when contacting the first user. As a result, even if the second user is unable to determine by himself whether to use a communication service when contacting the first user, he or she can contact the first user using the proposed communication service, thereby improving convenience for the second user.

[0013] In the present invention, in the proposing step, it is preferable that the second user be further proposed the timing of use in addition to the use of at least one communication service.

[0014] According to this communication data analysis method, the use and timing of at least one communication service are proposed to the second user by executing the proposing step. As a result, even if the second user is unable to determine the timing of use of the communication service when contacting the first user, the second user can contact the first user using the communication service at the proposed timing, thereby improving convenience for the second user.

[0015] In the present invention, the first user is composed of multiple types of corporate users, and in the analysis process, the relationship level is estimated by a machine learning model based on at least one of the order of the communication data and the date and time of communication occurrence, the type of communication service in the communication data, and the industry of each of the multiple types of corporate users. The machine learning model was trained for each industry of multiple corporate users. It is preferable that

[0016] According to this communication data analysis method, by executing an analysis process, a relationship level is estimated based on at least one of the order of the communication data and the date and time of communication occurrence, the type of communication service in the communication data, and the business type of each of multiple types of corporate users. This makes it possible to estimate the relationship level according to the business type of the corporate user, thereby improving the accuracy of the relationship level estimation.

[0017] In the present invention, in the analysis process, the relationship level is estimated by a machine learning model based on the content of the communication data in addition to at least one of the order of the communication data and the date and time of communication occurrence and the type of communication service in the communication data. The machine learning model is a model that learns the correlation between at least one of the order and date and time of communication of a predetermined number of communication data communicated between a pair of users, the type of communication service in the communication data, the content of the communication data, and the relationship level of one user to the other user, using as learning data the order and date and time of communication, the type, and the content of the communication data. It is preferable that

[0018] According to this communication data analysis method, by executing an analysis process, a relationship level is estimated based on the content of the communication data in addition to at least one of the order of the communication data and the date and time of communication occurrence, and the type of communication service in the communication data. As a result, the relationship level can be estimated based on the content of the communication data in addition to at least one of the order of the communication data and the date and time of communication occurrence, and the type of communication service in the communication data, thereby improving the accuracy of estimating the relationship level. Note that in this specification, "content of the communication data" refers to the content of data that has been converted into text (documented) from a telephone conversation if the communication service is a telephone call, and refers to the content of a message if the communication service is e-mail or the like.

[0019] In the present invention, the first user is composed of a plurality of types of corporate users, and in the analysis process, at least one of the order of communication data and the date and time of communication occurrence and the type of communication service in the communication data are analyzed. and the content of communication data In addition, the relationship level is estimated by a machine learning model based on the industry of each of the multiple types of corporate users. The machine learning model was trained for each industry of multiple corporate users. It is preferable that

[0020] According to this communication data analysis method, by executing an analysis process, a relationship level is estimated based on at least one of the order of the communication data and the date and time of communication occurrence, the type of communication service in the communication data, and the business type of each of multiple types of corporate users. This makes it possible to estimate the relationship level according to the business type of the corporate user, thereby improving the accuracy of the relationship level estimation.

[0021] In the present invention, the plurality of types of communication services are preferably a plurality of services selected from the group consisting of a telephone service, a social networking service (SNS), a short message service (SMS), and an email service.

[0022] According to this communication data analysis method, the communication data analysis method can be applied to general telephone services, SNS, SMS, and email services as communication services, thereby improving the versatility of the communication data analysis method. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a diagram showing the configuration of a communication system in which a communication data analysis method according to an embodiment of the present invention is executed; [Figure 2] 10 is a flowchart showing communication data processing. [Figure 3] FIG. 10 is a diagram illustrating an example of a communication data acquisition result. [Figure 4] 10 is a flowchart showing a communication data analysis process. [Figure 5] FIG. 10 is a diagram illustrating an example of input data. [Figure 6] FIG. 10 is a diagram illustrating an example of proposal data. [Figure 7] FIG. 10 is a diagram illustrating another example of input data. [Figure 8] FIG. 10 is a diagram showing another example of the communication data acquisition result. DETAILED DESCRIPTION OF THE INVENTION

[0024] A communication data analysis method according to an embodiment of the present invention will be described below with reference to the drawings. The communication data analysis method of this embodiment is executed in a communication system 1 shown in FIG.

[0025] 1, the communication system 1 includes a plurality of first communication device sets 10 (only one set is shown), a plurality of second communication device sets 20, and a server 3. In this communication system 1, the plurality of first communication device sets 10, the second communication device sets 20, and the server 3 are configured to be able to communicate with each other via a communication network 4.

[0026] The communication network 4 is configured to include a fixed telephone network, a wireless telephone network, a wired LAN network, a wireless LAN network, the Internet, and the like.

[0027] The multiple first communication equipment sets 10 are used by multiple first users M1 (only one is shown), respectively, and in this embodiment, an example will be described in which each of the multiple first users M1 uses each of the multiple first communication equipment sets 10 to conduct communication for commercial purposes with a second user M2.

[0028] Each first communication equipment set 10 is composed of a fixed telephone 11, a personal computer 12, and a smartphone 13. This fixed telephone 11 is configured to be able to communicate with a fixed telephone 21 of a second communication equipment set 20 via a communication network 4.

[0029] The personal computer 12 is configured to be able to communicate with the personal computer 22 or the smartphone 23 of the second communication device set 20 via the communication network 4. The smartphone 13 is configured to be able to communicate with the smartphone 23 or the personal computer 22 of the second communication device set 20 via the communication network 4.

[0030] On the other hand, the second communication equipment set 20 is used by the second user M2, and in this embodiment, we will explain an example in which the second user M2 uses the second communication equipment set 20 to conduct communication with the first user M1 for commercial or other purposes.

[0031] The second communication equipment set 20 is composed of a fixed telephone 21, a personal computer 22, and a smartphone 23. The fixed telephone 21 is configured to be able to communicate with the fixed telephone 11 of the first communication equipment set 10 via the communication network 4.

[0032] The personal computer 22 is configured to be able to communicate with the above-mentioned personal computer 12 or smartphone 13 of the first communication equipment set 10 via the communication network 4. The smartphone 23 is configured to be able to communicate with the above-mentioned smartphone 13 or personal computer 12 of the first communication equipment set 10 via the communication network 4.

[0033] With the above configuration, the communication system 1 is configured to enable communication between each first user M1 and second user M2 using the following communication services (hereinafter referred to as "communication services"). That is, communication between the fixed-line telephones 11 and 21 is enabled using the fixed-line telephone service, and communication between the smartphones 13 and 23 is enabled using the mobile phone service and SMS (Short Message Service).

[0034] Furthermore, communication via email services and SNS (Social Networking Service) is enabled between the personal computer 12 and the personal computer 22 or the smartphone 23, and between the smartphone 13 and the smartphone 23 or the personal computer 22. In the following explanation, an example will be given in which LINE (registered trademark) is used as the SNS.

[0035] On the other hand, the server 3 is configured as a physical server and includes a processor, storage, an I / O interface, a communication circuit, etc. (none of which are shown). As will be described later, the server 3 is configured to acquire communication data between the first user M1 and the second user M2 via the various communication services described above, and analyze the communication data. In this embodiment, the server 3 corresponds to a processing device.

[0036] The server 3 stores large language models as machine learning models, and these large language models are used when performing the analysis process of the communication data, as will be described later. In this case, the large language models stored are those for which a learning process of model parameters has been fully executed, and the learning process is specifically executed as will be described below.

[0037] That is, first, as a set of learning data, a predetermined number of (for example, several tens to several hundreds) of communication data are acquired between two users, starting from a predetermined communication occurrence timing (in this embodiment, the first communication occurrence timing). In this case, the communication data is data communicated between two communication device sets similar to the first communication device set 10 and the second communication device set 20 described above.

[0038] Then, the type of communication service in the acquired communication data, the order of the communication data (communication order), and the date and time of communication occurrence are acquired, and learning data is created by adding a relationship level to this data as a label, which represents the relationship between one user and the other user at the time when a predetermined number of communications have been completed.

[0039] In this case, the relationship level is set as an integer value within a predetermined range, and the higher the relationship between the two, the higher the value is set. In this embodiment, the predetermined range is a range of values ​​1 to 5. Note that the predetermined range is not limited to the range of values ​​1 to 5, and a different range (for example, a range of values ​​1 to 3, values ​​1 to 4, or values ​​1 to 6) may be used. Then, using this training data, model parameters of the large-scale language model are trained.

[0040] Similarly, a large number of sets (e.g., hundreds to thousands of sets) of training data are used to train the model parameters of a large-scale language model, thereby generating a large-scale language model in which the model parameter training process has been fully performed. In the case of a large-scale language model generated in this manner, when the type of communication service, the order of communication data, and the date and time of communication occurrence in a predetermined number of communication data between two users are input, the relationship level of one user with the other user is output as a value within the above-mentioned predetermined range.

[0041] The server 3 also stores, in a linked state, the user ID, user name, landline telephone number, mobile phone number, email address, and LINE account of each of the first users M1. The server 3 also stores, in a linked state, the user ID, user name, landline telephone number, mobile phone number, email address, and LINE account of the second user M2.

[0042] Furthermore, the server 3 stores a database for creating proposal data (see FIG. 6) to be described later based on the relationship level.

[0043] Next, we will explain various processes executed by the server 3. First, we will explain communication data processing with reference to Fig. 2. This communication data processing is executed when communication occurs between any one of the multiple first users M1 (hereinafter referred to as "acquisition target first user M1") and a second user M2 using the various communication services described above.

[0044] As shown in FIG. 2, first, a communication data acquisition process is executed (FIG. 2 / STEP 1). In this communication data acquisition process, when communication occurs between a first user M1 to be acquired and a second user M2, the communication data is acquired. Specifically, the communication data includes the date and time of communication occurrence, the user name, user ID, person in charge ID (ID of second user M2), and type of service (see FIG. 3). In this embodiment, the communication data acquisition process corresponds to the acquisition step.

[0045] Next, a storage process for communication data is executed (FIG. 2 / STEP 2). In this storage process for communication data, the communication data acquired as described above is stored in the server 3. By repeatedly executing the above process, a large amount of communication data is stored in the server 3, as shown in FIG.

[0046] Next, the communication data analysis process will be described with reference to Fig. 4. This communication data analysis process analyzes the communication data stored in the server 3, as will be described below.

[0047] As shown in Fig. 4, first, it is determined whether or not the execution conditions for the communication data analysis process are met (Fig. 4 / STEP 10). Specifically, if the following condition (a) is met, it is determined that the execution conditions are met, and otherwise it is determined that the execution conditions are not met.

[0048] (a) Among the multiple first users M1, there is a first user M1 (hereinafter referred to as the "first user M1 to be analyzed") who has not yet performed this communication data analysis process and whose number of communications with a second user M2 has reached a predetermined number, starting from a predetermined communication occurrence timing (in this embodiment, the first communication occurrence timing).

[0049] If the determination is negative (FIG. 4 / STEP 10...NO), and the execution condition is not met, the process ends. On the other hand, if the determination is positive (FIG. 4 / STEP 10...YES), and the execution condition is met, the input data creation process is executed (FIG. 4 / STEP 11).

[0050] In this input data creation process, input data to be input into the large-scale language model is created based on communication data between the first user M1 to be analyzed and the second user M2 stored in the server 3. This input data is a list of the order of occurrence, the date and time of communication occurrence, and the type of communication service, as shown in Figure 5.

[0051] Next, a relationship level acquisition process is executed (FIG. 4 / STEP 12). In this relationship level acquisition process, the input data is input into a large-scale language model, and a relationship level is acquired (estimated) as an output from the large-scale language model. This relationship level represents the level of the relationship between the first user M1 to be analyzed and the second user M2. In the following explanation, a case where the relationship level is acquired as a value of "3.1" will be taken as an example. In this embodiment, the relationship level acquisition process corresponds to the analysis step.

[0052] Next, a proposed data creation process is executed (FIG. 4 / STEP 13). In this proposed data creation process, proposed data is created by referring to the database in the server 3 based on the relationship level acquired as described above. This proposed data is intended to suggest to the second user M2 the timing of contacting the first user M1 to be analyzed and the communication service to be used for the contact.

[0053] In the database, the relationship between the relationship level and the proposed content of the time of contact and the communication service to be used for contact is defined, and the proposed data is created as shown in Fig. 6. That is, in the proposed data, the value of the relationship level, the name of the first user M1 to be analyzed as the contact target, the time of contact and the type of contact service are set as the proposed content.

[0054] Next, a proposed data transmission process is executed (FIG. 4 / STEP 14). In this proposed data transmission process, the proposed data described above is transmitted to the personal computer 22 and smartphone 23 of the second user M2. As a result, the proposed data shown in FIG. 6 is displayed on the displays of the personal computer 22 and smartphone 23. In this embodiment, the proposed data transmission process corresponds to a notification step and a proposal step.

[0055] As described above, according to the communication data analysis method of this embodiment, communication data of telephone services via landline and mobile phones, SMS, email services, and SNS between a first user and a second user is acquired by the server 3. Then, if an analysis target first user M1 (first user M1 who has communicated with a second user M2 a predetermined number of times since a predetermined communication occurrence timing) exists, an input data creation process (FIG. 4 / STEP 11) and a relationship level analysis process (FIG. 4 / STEP 12) are executed, and a relationship level indicating the level of the relationship between the first user and the second user is estimated.

[0056] Here, the order of communication data exchanged between the first user and the second user, the date and time of communication, and the type of communication service in the communication data can be considered to represent the transition and level of the relationship of the first user with the second user. Therefore, by inputting the above input data into a machine learning model and estimating the relationship level of the first user with the second user, it is possible to accurately estimate this.

[0057] Furthermore, the proposed data is transmitted to the second user M2 by executing the proposed data creation process (FIG. 4 / STEP 13) and the proposed data transmission process (FIG. 4 / STEP 14). This proposed data includes the relationship level estimation result, the contact timing, and the contact service, and this proposed data is displayed on the personal computer 12 and smartphone 13 of the first user M1. As a result, even if the second user is unable to appropriately judge the relationship with the first user M1 to be analyzed by himself, he or she can know the objective judgment result regarding the relationship level between the first user M1 to be analyzed and the second user.

[0058] Furthermore, even if the second user is unable to determine for himself or herself when and which communication service to use when contacting the first user M1 to be analyzed, the second user can contact the first user M1 to be analyzed using the proposed communication service at the proposed communication time, thereby improving convenience for the second user.

[0059] In addition, if the multiple first users M1 are composed of multiple types of corporate users, the relationship level may be estimated using a machine learning model (e.g., a large-scale language model) based on the order of the communication data and the type of communication service in the communication data, as well as the industry of each of the multiple types of corporate users (e.g., finance, manufacturing, sales, etc.).

[0060] In this case, a machine learning model is created by performing learning of the model parameters of the above-mentioned machine learning model for each industry and stored in server 3, and in STEP 12 of Figure 4, the relationship level is estimated by using the machine learning model corresponding to the industry of the first user M1 to be analyzed.

[0061] In this configuration, the relationship level can be estimated according to the business type of the corporate user, thereby improving the accuracy of estimating the relationship level.

[0062] Furthermore, a machine learning model that outputs a relationship level when the content of the communication data (hereinafter referred to as "communication content") is input in addition to the order of the communication data, the date and time of communication, and the type of communication service in the communication data may be used. For example, in STEP 12 of Fig. 4, a machine learning model that outputs a relationship level when input data such as that shown in Fig. 7 is input may be used. In the data shown in Fig. 7, the content of communication via landline and mobile phones has been converted into text by speech recognition processing in server 3.

[0063] Furthermore, when learning the model parameters of the machine learning model, the learning data is data in which the order of the communication data, the date and time of communication, the type of communication service in the communication data, and the communication content (for example, the content shown in Figure 8) are labeled with a relationship level.

[0064] When configured as described above, the relationship level can be estimated based on the communication content in addition to the order of the communication data and the type of communication service in the communication data, thereby improving the accuracy of estimating the relationship level.

[0065] In addition, if the first users M1 are composed of multiple types of corporate users, a machine learning model can be created by learning the model parameters of the above machine learning model for each industry, which can further improve the accuracy of estimating the relationship level.

[0066] Furthermore, although the embodiment is an example in which a physical server is used as the server 3, a virtual server may be used instead as the server 3. In that case, the physical server that constitutes the virtual server corresponds to the arithmetic processing device.

[0067] Furthermore, although the embodiment is an example in which a server 3 is used as the arithmetic processing device, it is also possible to use a personal computer as the arithmetic processing device, a combination of multiple personal computers, a combination of a personal computer and a server, or a cloud computing system.

[0068] On the other hand, the embodiment is an example in which a large-scale language model is used as the machine learning model, but instead, a neural network, a CNN (Convolutional neural network), an RNN (Recurrent Neural Network), or the like may be used as the machine learning model, or a regression model such as a random forest may be used.

[0069] In addition, the embodiment is an example in which the relationship level is estimated using a machine learning model based on the order of communication data communicated between the first user and the second user, the date and time of communication, and the type of communication service in the communication data, but the relationship level may also be configured to be estimated using a machine learning model based on either the order of the communication data or the date and time of communication, and the type of communication service in the communication data.

[0070] Furthermore, the embodiment is an example in which data communicated bidirectionally between the first user and the second user is used as the communication data communicated between the two users, but instead, only communication data communicated from the first user to the second user may be used as the communication data communicated between the first user and the second user.

[0071] Furthermore, although the embodiments are examples in which telephone services using landlines and mobile phones, SMS, email services, and SNS are used as communication services, two or more of these communication services may be used. In that case, the machine learning model may be obtained by learning model parameters using communication data from these two or more communication services as learning data.

[0072] In the execution condition determination process (STEP 10) of FIG. 4, it may be determined that the execution condition is met when the following condition (b) is met, instead of the above-mentioned condition (a). (b) When the first user M1 who wishes to perform the communication analysis process is determined by the second user M2, and data indicating the user name or user ID of the first user M1 is transmitted from the second communication equipment set 20 and then received by the server 3.

[0073] Furthermore, in the embodiment, the predetermined communication occurrence timing to be used as the starting point is the first communication occurrence timing, but the predetermined communication occurrence timing to be used as the starting point is not limited to this and can be set to an appropriate timing such as the second or third communication occurrence timing, in which case the predetermined communication occurrence timing in the training data of the large-scale language model can also be set to the same timing.

[0074] Furthermore, the proposed data in FIG. 6 is an example in which the contact time is set to within four days, but the contact time may be set by date or a predetermined period (for example, a period of two to four days later). [Explanation of symbols]

[0075] 1. Communication Systems 3 Server (processing unit) M1 First user M2 Second user

Claims

1. A communication data analysis method for analyzing, by a processing device, a plurality of types of communication data communicated between a first user and a second user via a plurality of types of communication services, comprising: The arithmetic processing device an acquisition step of acquiring the plurality of types of communication data; an analysis step of executing an analysis process to estimate a relationship level representing the level of the relationship of the first user with the second user using a machine learning model based on at least one of the order of communication data communicated between the first user and the second user and the date and time of communication occurrence and the type of communication service in the communication data among the acquired multiple types of communication data; Run The communication data analysis method is characterized in that the machine learning model is a model that learns the correlation between at least one of the order and the date and time of communication of a predetermined number of communication data communicated between a pair of users, the type of communication service in the communication data, and the relationship level of one user to the other user, using the order and the date and time of communication, as well as the type, and the relationship level as learning data.

2. 2. The communication data analysis method according to claim 1, The arithmetic processing device The communication data analysis method further comprises a notification step of notifying the second user of the estimation result of the relationship level.

3. 2. The communication data analysis method according to claim 1, The arithmetic processing device A communication data analysis method characterized by further performing a suggestion step for suggesting to the second user, based on the relationship level, the use of at least one of the plurality of communication services as a communication means when the second user contacts the first user.

4. 4. The communication data analysis method according to claim 3, The communication data analysis method, wherein in the proposing step, the second user is proposed the use of the at least one communication service as well as the timing of the use.

5. 2. The communication data analysis method according to claim 1, The first users are composed of multiple types of corporate users, In the analysis process, the relationship level is estimated by the machine learning model based on at least one of the order of the communication data and the communication occurrence date and time, the type of the communication service in the communication data, and the industry of each of the multiple types of corporate users; A communication data analysis method characterized in that the machine learning model is one that has been trained for each industry of the multiple types of corporate users.

6. 2. The communication data analysis method according to claim 1, In the analysis process, the relationship level is estimated by the machine learning model based on at least one of the order of the communication data and the date and time of communication occurrence, the type of the communication service in the communication data, and the content of the communication data; The communication data analysis method is characterized in that the machine learning model is a model that learns the correlation between at least one of the order and date and time of communication data exchanged between a predetermined number of users, the type of communication service in the communication data, the content of the communication data, and the relationship level of one user to the other user as learning data.

7. 7. The communication data analysis method according to claim 6, The first users are composed of multiple types of corporate users, In the analysis process, the relationship level is estimated by the machine learning model based on at least one of the order of the communication data and the date and time of communication occurrence, the type of the communication service in the communication data, the content of the communication data, and the industry of each of the multiple types of corporate users; A communication data analysis method characterized in that the machine learning model is one that has been trained for each industry of the multiple types of corporate users.

8. The communication data analysis method according to any one of claims 1 to 7, The communication data analysis method, wherein the plurality of types of communication services are a plurality of services selected from the group consisting of telephone service, SNS (Social Networking Service), SMS (Short Message Service), and email service.

Images