TW201510898A - User profile generating server and user profile generating method thereof - Google Patents

Abstract

A user profile generating server and a user profile generating method thereof are provided. The user profile analysis server comprises a transceiver, a storage and a processor. The transceiver receives a plurality of phone number messages. Each of the phone number messages carries a phone number. The storage stores a plurality of store information. Each of the phone numbers corresponds to one of the plurality of store information. The processor counts an occurrence number of each of the phone numbers in the phone number messages and analyzes the occurrence number of each of the phone numbers and the store information corresponding to each of the phone numbers to generate a user profile.

Description

User data generation server and user data generation method thereof

The invention relates to a user data generating server and a user data generating method thereof. Specifically, the user data generating server receives the plurality of phone number messages from a user device, and generates a user regarding the use of the user device according to the phone number and the corresponding store information contained in each phone number message. User profile.

With the development of technology, smart phones have replaced traditional mobile phones as the mainstream of the market because they can provide a variety of programs and services. Traditionally, the desire to obtain user data (eg, gender, occupation, interest, etc.) must require the user to manually electronically form, or in an intrusive manner, such as: obtaining user authorization, self-recording of user data. Obtained in social networking sites.

However, the above-mentioned manner of obtaining user data is not only cumbersome and inconvenient, but also more likely to bring a bad user experience. In view of this, how to automatically predict the user data of users of smart phones in a non-intrusive manner through smart phones is an urgent need for the industry.

An object of the present invention is to provide a user data generating server and a user data generating method thereof. The user data generating server of the present invention automatically generates the user data of the user of the smart phone in a non-intrusive manner by analyzing the object to which the user dials or answers the phone number and the phone number.

To achieve the above objective, the present invention discloses a user data generation server including a transceiver, a storage, and a processor. The transceiver is for receiving a plurality of phone number messages from a user device. Each phone number message carries a phone number. The storage is used to store multiple store information. Each of the phone numbers corresponds to one of the store information. The processor is configured to count, according to the phone number messages, the number of occurrences of each of the phone numbers in the phone number messages, and analyze the number of occurrences of the phone numbers and the corresponding store information to generate a use. Information.

In addition, the present invention further discloses a method for generating user data for a user data generation server. The user data generating server comprises a transceiver, a storage and a processor. The transceiver receives a plurality of phone number messages from a user device. Each phone number message carries a phone number. The storage stores a plurality of store information. Each of the phone numbers corresponds to one of the store information. The user data generating method is executed by the processor and includes the steps of: counting the number of occurrences of each of the phone numbers in the phone number messages according to the phone number messages; and analyzing the number of occurrences of each of the phone numbers And the corresponding store information to generate a user profile.

Other objects, advantages, and technical means and embodiments of the present invention will become apparent to those skilled in the <RTIgt;

11‧‧‧User data generation server
13‧‧‧Network
15‧‧‧User device
11a‧‧‧Transceiver
11b‧‧‧Storage
11c‧‧‧ processor
102‧‧‧Phone number message
104‧‧‧ User Information

1 is a diagram showing the connection relationship between a user profile generation server 11 and a user device 15 in the first embodiment of the present invention.

Figure 2 is a schematic diagram of the user data generation server 11 of the present invention.

Figure 3 is a flow chart showing a method of generating user data according to a second embodiment of the present invention.

The following examples are intended to illustrate the technical content of the present invention and are not intended to limit the scope of the present invention. Further, in the following embodiments and drawings, elements that are not related to the present invention have been omitted and are not shown, and the dimensional relationships between the elements in the drawings are merely for ease of understanding and are not intended to limit the actual ratio.

A first embodiment of the present invention, as shown in FIG. 1, depicts a connection relationship between a user profile generation server 11 and a user device 15. The user data generating server 11 receives a plurality of telephone number messages 102 from a user device 15 via the network 13. The network 13 can be a telecommunications network, an internet network, or a combination thereof.

Specifically, the user device 15 is a smart phone that installs an application related to the user profile generation server 11 (hereinafter referred to as an information provider). The information providing program enables the user device 15 to monitor the behavior of the user operating the user device 15, for example, calling a phone number to de-energize or receiving a call to a phone number, and causing the user device 15 to generate and transmit the phone. The number telephone number message 102 to the user data generation server 11. In addition, when the user data generating server 11 transmits a specific message to the user device 15, the information providing program is also used to present the information contained in the specific message.

As shown in FIG. 2, the user profile generation server 11 includes a transceiver 11a, a storage 11b, and a processor 11c. The processor 11c is electrically connected to the transceiver 11a and the storage 11b. The transceiver 11a receives the plurality of telephone number messages 102 from the user device 15 over time. Each phone number message 102 carries a phone number and a user identification code. The storage 11b stores a plurality of store information and a plurality of user identification codes. Each phone number corresponds to one of the store information. The user identification code is used to distinguish each user device. The processor 11c counts the number of occurrences of each phone number in the phone number message 102 according to the phone number message 102, and analyzes the number of occurrences of each phone number and the corresponding store information to generate a user profile 104. And stored in the storage 11b. Further, the processor 11c may employ a supervised learning algorithm (but is not limited thereto), establish a user data model and store it in the storage 11b, so that each phone is analyzed based on the user data model. After the number of occurrences of the number and the corresponding store information, the user profile 104 is generated by estimating information such as interest, gender, lifestyle, economic level, occupation, or age range of the messenger.

For example, the processor 11c can generate a call record of the user according to each phone number message 102, and retrieve the store information corresponding to each phone number message 102 from the storage device 11b, as shown in the following Table 1:

In this way, according to the user's call record, the processor 15c can estimate the user's gender, interest, lifestyle, lifestyle, economy, occupation, age range, etc. to generate the user profile 104. As shown in Table 1, according to the user's daily phone number PN1 between 7:00 and 8:00 and its corresponding A breakfast shop, the user's living habits can be estimated and based on the average consumption of the A breakfast shop. Can estimate the user's economic level. Furthermore, the user's gender can be estimated based on the user dialing or receiving the phone number PN2 and its corresponding B obstetrics and gynaecology. In addition, the user's interest can be estimated based on the user dialing the phone number PN3 and its corresponding C-cinema.

In detail, the processor 11c analyzes the name of the store information corresponding to each phone number, and obtains the category of the store (for example, food, clothing, housing, travel, entertainment, or more detailed categories), location, and average consumption. Etc., this can be achieved by means of data mining or searching for related databases in the storage 11b via the Internet, but is not limited thereto. After counting the number of occurrences of each telephone number, the processor 11c can estimate the user's gender, interest, lifestyle, and living habit by analyzing the frequency at which the user dials or receives some telephone numbers and the corresponding store information. , economic level, occupation, age range, and then generate user data 104.

In addition, in one aspect, the processor 11c calculates the probability of occurrence of one of the phone numbers based on the total number of messages of the ones of the phone number messages 102 and the number of occurrences of the phone numbers in the phone number messages 102. The phone numbers are obtained by capturing at least one popular phone number whose probability of occurrence is greater than a preset value, and generating the user profile 104 according to the store information corresponding to the at least one popular phone number.

For example, as shown in Table 1, the processor 11c calculates the total number of messages (for example, 1000 messages) in a calculation period (for example, one week) according to the number of the telephone number messages 102 received by the transceiver 11a. . Subsequently, the processor 11c calculates the number of times the user dials or receives the telephone number PN1, the telephone number PN2, the telephone number PN3, and the telephone number PN2 through the user device 15, thereby obtaining the telephone number PN1, the telephone number PN2, the telephone number PN3, and the telephone number. The probability of occurrence of PN2 in multiple phone number messages 102.

Next, the processor 11c retrieves at least one popular telephone number whose probability of occurrence is greater than a predetermined value (for example, 15%) from the telephone number PN1, the telephone number PN2, the telephone number PN3, and the telephone number PN2. In the present example, assuming that the popular telephone number is the telephone number PN1 and the telephone number PN3, the processor 11c can generate the user profile 104 only for the telephone number PN1, the telephone number PN3, and the corresponding store information. It should be noted that the calculation period will change with time, and the probability of occurrence of each telephone number will also change. Usually, the calculation period refers to a specific period of time when the user data generation server 11 operates at the current moment.

In addition, in one aspect, each phone number message 102 further contains a call message, which may include a time stamp, a call time, a call location, a call behavior, a call behavior, a rejection behavior, and a Missing behavior, an interrupted call behavior, or a user setting, etc., wherein the user setting includes setting a phone number as a common phone number, a blacklist, and adding annotations, comments, and the like to the phone number. . In this case, the processor 11c generates the user profile 102 based on the call information.

For example, the user device 15 can generate the phone number message 102 and transmit it to the user profile generation server 11 after the user ends the call. The phone number message 102 generated by the user device 15 may include additional call information, such as: recording the call start time as AM 7:30, the call end time is AM 7:40, the call time is 10 minutes, and the call location is a business. The area, the dialing behavior, and the telephone number are set as common telephone numbers and the like in the user device 15. In this way, the processor 11c of the user data generating server 11 can further generate the user profile 104 more in line with the user according to the call information.

For example, if the processor 11c analyzes the call information of the continuous phone number message 102, it analyzes the store corresponding to most of the phone numbers dialed by the user device 15 in a short period of time (for example, within 10 minutes). In the information, the locations are all located in the same area, and the categories of the stores are all in the same category (for example, Japanese restaurants with food or more details), the processor 11c can estimate that the user wants to find in this area. The vacant Japanese restaurant further performs data mining from the Internet or the related database in the search storage 11b periodically through the transceiver 11a to generate a specific message and enables the transceiver 11a to transmit the specific message to The user device 15 wherein the specific message carries information of a plurality of Japanese restaurants in the area.

For example, if the processor 11c analyzes the store information corresponding to most phone numbers rejected by the user device 15 according to the call information of the continuous phone number message 102, the categories of the store are all in the same category (for example, : Bank), the processor 11c can estimate that the user is not willing to answer the bank's marketing call. In this way, the processor 11c can generate a suggestion message and enable the transceiver 11a to transmit the suggestion message to the user device 15, wherein the information providing program can display the option of adding the bank phone number to the blacklist according to the suggestion message. For the user to choose.

In addition, in one aspect, the user device 15 can upload the address book set by the user to the user data generation server 11. In this case, the storage 11b further stores the address book with the user device 15, so that the processor 11c can generate the user profile 104 based on the address book. For example, when the user's address book includes a plurality of store names, the processor 11c can determine the categories of the stores (for example, KTV, record line, etc.) by analyzing the store name, so that the user's interest can be estimated. .

In addition, in one aspect, the processor 11c performs a feature classification on the basis of the user data. For example, the processor 11c is obtained from the user profile 104, and the user's interest is music, so the user is classified into characteristics and classified into music categories. According to this, the processor 11c can select the latest activity information about the music (for example, concert, concert) from the storage 11b, and generate an advertisement message and transmit it to the user device 15. In detail, the processor 11c can periodically perform data mining from the Internet through the transceiver 11a or receive various activity messages from other information providing machines, and classify the collected information into characteristics and store them in the storage 11b. And after each update, the latest activity information related to the user's category is provided to the user as an advertisement message. The delivery method of the advertisement message can be transmitted to the user device 15 through the information provider, the newsletter or various communication applications.

For example, the processor 11c can generate a category message according to the category of the user, and enable the transceiver 11a to transmit the category message to an information providing server. The category message contains contact information (eg, mobile number, account number of the communication application) of the user device 15. Accordingly, the information providing server can provide an advertisement message to the user device 15 according to the category message.

A second embodiment of the present invention is shown in FIG. 3, which is a flow chart of a method for generating user data. The user data generating method is applicable to a user data generating server, which includes a transceiver, a storage, and a processor. The transceiver receives a plurality of phone number messages from a user device. Each phone number message contains a phone number. The storage stores multiple store information. Each phone number corresponds to one of the store information. The user data generation method is performed by the processor.

First, in step S301, according to the plurality of phone number messages, the number of occurrences of each phone number in one of the phone number messages is counted. Next, in step S303, the number of occurrences of each telephone number and the corresponding store information are analyzed to generate a user profile.

In addition to the above steps, the second embodiment can also perform all the operations and functions described in the first embodiment, and those skilled in the art can directly understand how the user data generating method for the user data generating server of the present invention is directly known. The above-described first embodiment is used to perform such operations and functions, and thus will not be described herein.

In summary, the present invention provides a user data generating server and a user data generating method thereof. The user data generating server can automatically generate the user's user data in a non-intrusive manner by analyzing the telephone number and the telephone number that the user dials or receives, and can further use the user data according to the use. Predicting the user's behavioral intentions, such as the call behavior, the call behavior, the rejection behavior, the missed behavior, or the interruption of the call behavior.

It is to be understood that the above-described embodiments are merely illustrative of the embodiments of the invention and the technical features of the invention are not intended to limit the scope of the invention. Any changes or equivalents that can be easily made by those skilled in the art are within the scope of the invention. The scope of the invention should be determined by the scope of the claims.

Claims (1)

A user data generation server includes:

a transceiver for receiving a plurality of phone number messages from a user device, each of the phone number messages carrying a phone number;

a storage for storing a plurality of store information, each of the phone numbers corresponding to one of the store information;

a processor for counting the number of occurrences of each of the phone numbers in the phone number messages according to the phone number messages, and analyzing the number of occurrences of the phone numbers and the corresponding store information to generate A user profile.

2. The user data generation server according to claim 1, wherein the user data is selected from the group consisting of an interest, a gender, a lifestyle, an economic level, a occupation, and an age interval. group.

3. The user data generating server according to claim 2, wherein the processor further calculates the total number of messages according to one of the phone number messages and the number of occurrences of the phone numbers in the phone number messages. One of each of the telephone numbers has a probability that, from the telephone numbers, the at least one popular telephone number having a probability of occurrence greater than a predetermined value is retrieved, and the use is generated according to the store information corresponding to the at least one popular telephone number. Information.

4. The user data generating server according to claim 3, wherein each of the phone number messages further includes a call information selected from a time stamp, a call time, a call location, and a call. The behavior, a call-receiving behavior, a reject behavior, a missed call behavior, an interrupted call behavior, and a user-defined group, the processor generates the user profile based on the call information.

5. The user data generating server of claim 3, wherein the storage further stores an address book of the user device, and the processor further generates the user data according to the address book.

6. The user data generating server according to claim 1, wherein the processor further performs a feature classification according to the user data.

7. A user data generating method for a user data generating server, the user data generating server comprising a transceiver, a storage and a processor, the transceiver receiving a plurality of calls from a user device The number message, each of the phone number messages carries a phone number, the store stores a plurality of store information, each of the phone numbers corresponding to one of the store information, the user data generating method is performed by the processor and includes the following steps :

Counting the number of occurrences of each of the telephone numbers in one of the telephone number messages based on the telephone number messages;

The number of occurrences of each of the phone numbers and the corresponding store information are analyzed to generate a user profile.

8. The method of generating user data according to claim 7, wherein the user data is selected from the group consisting of an interest, a gender, a lifestyle, an economic level, a occupation, and an age interval. group.

9. The method for generating user data as described in claim 8 further includes the following steps:

The total number of messages based on one of the phone number messages and the number of occurrences of the phone number in the phone number messages;

Calculate the probability of occurrence of one of the phone numbers;

Retrieving at least one popular telephone number having a probability of occurrence greater than a predetermined value from the telephone numbers;

The user profile is generated according to the store information corresponding to the at least one popular phone number.

10. The user data generating method of claim 9, wherein each of the phone number messages further includes a call information selected from a time stamp, a call time, a call location, and a call behavior. The user data generating method further comprises the following steps: a receiving behavior, a rejecting behavior, a missed behavior, an interrupted calling behavior, and a group set by a user.

The user profile is generated based on the call information.

11. The user data generating method of claim 9, wherein the storage further stores an address book of the user device, and the user data generating method further comprises the following steps:

According to the address book, the user profile is generated.

12. The method for generating user data as described in claim 7 further includes the following steps:

According to the user data, a feature classification is performed.