KR20230115177A - Service providing server that provides sentiment analysis service for marketing and the operating method thereof - Google Patents

Abstract

A service providing server providing emotion analysis service for marketing and an operating method thereof are disclosed. The present invention provides a service providing server that can analyze emotions contained in sentences collected as customer feedback on a given service and provide the analysis result to the business owner of the corresponding service, and its operation method, so that the business owner can Based on the result of sentiment analysis on customer feedback, service quality can be improved or marketing strategy can be established.

Description

Service providing server providing sentiment analysis service for marketing and its operating method

The present invention relates to a service providing server that provides an emotion analysis service for marketing and a method of operating the same.

Recently, as the importance of marketing increases, various marketing strategies are appearing.

As one of these marketing strategies, a method of analyzing customers' feedback on a specific service and promoting service quality improvement based on this feedback is drawing attention.

For example, in the case of a restaurant, a strategy of analyzing customers' evaluation information of the corresponding restaurant and improving the menu based on the analysis may be used.

In order to analyze these customers' feedback, it is necessary to introduce a technique that analyzes the sentences left by customers as feedback and determines whether the emotion contained in the sentence is positive or negative.

Therefore, by analyzing the emotions contained in the sentences collected as customer feedback on a given service and providing the analysis result to the business owner for the corresponding service, the business owner can improve service quality based on the customer feedback analysis result. There is a need for research on sentiment analysis services that can help improve or establish marketing strategies.

The present invention provides a service providing server that can analyze emotions contained in sentences collected as customer feedback on a given service and provide the analysis result to the business owner of the corresponding service, and its operation method, so that the business owner can Based on the results of sentiment analysis on customer feedback, we want to help improve service quality or establish marketing strategies.

A service providing server providing a sentiment analysis service for marketing according to an embodiment of the present invention has preset n (n is a natural number of 5 or more) words - each of the n words is assigned a preset sequence number. - In this stored dictionary database, a reference in which a preset n-dimensional first reference vector corresponding to positive emotion information and a preset n-dimensional second reference vector corresponding to negative emotion information are stored. A vector storage unit receives a plurality of pre-collected sentences as customer feedback on service quality from a first electronic terminal of a first merchant among a plurality of merchant owners subscribed to the emotion analysis service, and the plurality of sentences When a sentiment analysis request based on the sentiment is received, for each of the plurality of sentences, after counting the frequency of each of the n words in each sentence, the frequency of each of the n words appears, the n words A sentence vector generator for generating a sentence vector corresponding to each of the plurality of sentences by constructing an n-dimensional vector designated as a vector component according to the order assigned to each of the plurality of sentences, for each of the plurality of sentences, Corresponds to each of the plurality of sentences by determining which emotion information has a reference vector having a greater cosine similarity with the sentence vector corresponding to each sentence, among the emotion information corresponding to positive and the emotion information corresponding to the negative. An emotion information specifying unit for designating emotional information to be used, and an emotion information transmission unit for transmitting emotion information corresponding to each of the plurality of sentences to the first electronic terminal when the emotion information corresponding to each of the plurality of sentences is designated. include

In addition, a method of operating a service providing server that provides a sentiment analysis service for marketing according to an embodiment of the present invention includes preset n (n is a natural number of 5 or more) words - each of the n words includes a preset number of words. A sequence number is assigned - maintaining a dictionary database in which this is stored, a first reference vector of a preset n dimension corresponding to emotion information corresponding to positive and a preset n dimension corresponding to emotion information corresponding to negative Maintaining a reference vector storage unit in which a second reference vector is stored, a plurality of previously collected customer feedbacks on service quality from a first electronic terminal of a first affiliated store owner among a plurality of affiliated store owners subscribed to the emotion analysis service While sentences of are received, when a request for emotion analysis based on the plurality of sentences is received, for each of the plurality of sentences, after counting the number of times each of the n words appears in each sentence, the n words Generating a sentence vector corresponding to each of the plurality of sentences by configuring an n-dimensional vector in which the frequency of each occurrence of each is designated as a vector component according to the order assigned to each of the n words; For each of a plurality of sentences, among the emotion information corresponding to the positive and the emotion information corresponding to the negative, it is determined which emotion information has a reference vector having a greater cosine similarity with the sentence vector corresponding to each sentence. , the step of designating emotion information corresponding to each of the plurality of sentences, and when the emotion information corresponding to each of the plurality of sentences is designated, the emotion information corresponding to each of the plurality of sentences to the first electronic terminal It includes sending.

The present invention provides a service providing server that can analyze emotions contained in sentences collected as customer feedback on a given service and provide the analysis result to the business owner of the corresponding service, and its operation method, so that the business owner can Based on the result of sentiment analysis on customer feedback, service quality can be improved or marketing strategy can be established.

1 is a diagram showing the structure of a service providing server that provides a sentiment analysis service for marketing according to an embodiment of the present invention.
2 is a flowchart illustrating an operating method of a service providing server providing an emotion analysis service for marketing according to an embodiment of the present invention.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings. This description is not intended to limit the present invention to specific embodiments, but should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention. While describing each drawing, similar reference numerals have been used for similar components, and unless otherwise defined, all terms used in this specification, including technical or scientific terms, are common knowledge in the art to which the present invention belongs. has the same meaning as commonly understood by the person who has it.

In this document, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated. In addition, in various embodiments of the present invention, each component, functional block, or means may be composed of one or more sub-components, and the electrical, electronic, and mechanical functions performed by each component are electronic It may be implemented with various known elements or mechanical elements such as circuits, integrated circuits, ASICs (Application Specific Integrated Circuits), and may be implemented separately or two or more may be integrated into one.

On the other hand, the blocks of the accompanying block diagram or the steps of the flowchart are computer program instructions that perform designated functions by being loaded into a processor or memory of a device capable of data processing, such as a general-purpose computer, a special purpose computer, a portable notebook computer, and a network computer. can be interpreted as meaning Since these computer program instructions may be stored in a memory included in a computer device or in a computer readable memory, the functions described in blocks of a block diagram or steps of a flowchart are produced as a product containing instruction means for performing them. It could be. Further, each block or each step may represent a module, segment or portion of code that includes one or more executable instructions for executing specified logical function(s). Also, it should be noted that in some alternative embodiments, functions mentioned in blocks or steps may be executed out of a predetermined order. For example, two blocks or steps shown in succession may be performed substantially simultaneously or in reverse order, and in some cases, some blocks or steps may be omitted.

1 is a diagram showing the structure of a service providing server that provides a sentiment analysis service for marketing according to an embodiment of the present invention.

Referring to FIG. 1, the service providing server 110 according to the present invention includes a dictionary database 111, a reference vector storage unit 112, a sentence vector generator 113, an emotion information storage unit 114, and emotion information transmission. Includes section 115.

In the dictionary database 111, preset n (n is a natural number equal to or greater than 5) words (each of the n words is assigned a preset order number) are stored.

For example, when n is '100', 100 words may be stored in the dictionary database as shown in Table 1 below.

100 words The sequence number assigned to each word word 1 One word 2 2 word 3 3 ... ... word 100 100

The reference vector storage unit 112 stores a preset n-dimensional first reference vector corresponding to positive emotion information and a preset n-dimensional second reference vector corresponding to negative emotion information.

The sentence vector generator 113 generates a plurality of pre-collected customer feedback on service quality from the first electronic terminal 10 of the first affiliated store owner 11 among the plurality of affiliated store owners subscribed to the sentiment analysis service. While sentences are received, if a request for emotion analysis based on the plurality of sentences is received, for each of the plurality of sentences, after counting the frequency of each of the n words in each sentence, the n words A sentence vector corresponding to each of the plurality of sentences is generated by configuring an n-dimensional vector in which the frequency of each occurrence is designated as a vector component according to the order assigned to each of the n words.

For example, if n is '100' and 100 words are stored in the dictionary database 111 as shown in Table 1 above, the sentence vector generator 113 generates each of the plurality of sentences. After counting the frequency of each of the 100 words in the sentence, a 100-dimensional vector designating the frequency of each of the 100 words as a vector component according to the order assigned to each of the 100 words By constructing, it is possible to generate a sentence vector corresponding to each of the plurality of sentences.

In this regard, when it is assumed that 'sentence 1' among the plurality of sentences exists, the sentence vector generator 113 counts the frequency of occurrence of each of the 100 words in 'sentence 1' and then generates the 100 words A sentence vector corresponding to 'sentence 1' can be generated by constructing a 100-dimensional vector in which the frequency of occurrence of each of . is designated as a vector component according to the order assigned to each of the 100 words. In this way, the sentence vector generator 113 may generate a 100-dimensional sentence vector corresponding to each of the plurality of sentences.

At this time, according to one embodiment of the present invention, when the sentence vector generator 113 receives the plurality of sentences and the emotion analysis request from the first electronic terminal 10, for each of the plurality of sentences, After preprocessing each of the plurality of sentences by removing text that does not match the n words from each sentence, counting the frequency of each of the n words from the plurality of preprocessed sentences and constructing a vector , Sentence vectors corresponding to each of the plurality of sentences may be generated. Through this, the sentence vector generator 113 can more quickly count the frequency of each of the n words by removing unnecessary text from each of the plurality of sentences.

For each of the plurality of sentences, the emotion information specifying unit 114 selects a reference vector having a greater cosine similarity with the sentence vector corresponding to each sentence, among the emotion information corresponding to the positive and the emotion information corresponding to the negative, for each of the plurality of sentences. Emotion information corresponding to each of the plurality of sentences is designated by checking which emotion information has .

For example, when it is assumed that 'sentence 1' exists among the plurality of sentences, the emotion information specifying unit 114 calculates the cosine similarity between the sentence vector corresponding to 'sentence 1' and the first reference vector, and After calculating the cosine similarity between the sentence vector corresponding to 1' and the second reference vector, the emotion information for the corresponding reference vector corresponds to 'sentence 1' by checking which reference vector has a higher cosine similarity. can be specified as emotional information.

In this regard, when it is assumed that the cosine similarity with the first reference vector is greater than the cosine similarity with the second reference vector, the emotion information specifying unit 114 uses emotion information corresponding to 'sentence 1' as emotion corresponding to affirmation. information can be specified.

In this way, the emotion information specifying unit 114 may designate emotion information corresponding to each of the plurality of sentences.

When the emotion information corresponding to each of the plurality of sentences is designated, the emotion information transmission unit 115 transmits the emotion information corresponding to each of the plurality of sentences to the first electronic terminal 10 .

At this time, according to an embodiment of the present invention, when the emotion information corresponding to each of the plurality of sentences is designated, the emotion information transmission unit 115 maps the plurality of sentences and the emotion information corresponding to each sentence to each other. After generating an emotion analysis table recorded by the user, the emotion analysis table may be encrypted and transmitted to the first electronic terminal 10 .

In this regard, the emotion information transmission unit 115 generates the emotion analysis table in which the plurality of sentences and the emotion information corresponding to each sentence are recorded in correspondence with each other in the form shown in Table 2 below, and then encrypts and 1 can be transmitted to the electronic terminal (10).

plural sentences emotion information sentence 1 Positive sentence 2 denial sentence 3 Positive ... ...

At this time, according to an embodiment of the present invention, the emotion information transmission unit 115 includes an identification number storage unit 116, a hash function storage unit 117, an encryption event generation unit 118, a calculation unit 119, and a transmission processing unit. (120).

The identification number storage unit 116 stores different identification numbers of t (t is a natural number equal to or greater than 2) digits previously issued to each of the plurality of affiliated store owners.

For example, information may be stored in the identification number storage unit 116 as shown in Table 3 below.

multiple store owners identification number Franchise Owner 1 1 2 3 4 5 franchise owner 2 14592 Franchise Owner 3 23456 ... ...

The hash function storage unit 117 stores a hash function previously shared with electronic terminals of each of the plurality of affiliate store owners.

When the emotion analysis table is generated, the encryption event generating unit 118 generates an encryption event to encrypt the emotion analysis table and transmit it to the first electronic terminal 10 .

When the encryption event occurs, the operation unit 119 checks the first identification number corresponding to the first affiliated store owner from the identification number storage unit 116, and for each of the t numbers constituting the first identification number A t-bit identification code is generated by configuring the resultant value when performing a modulo-2 operation on a bit string, and after randomly generating a t-bit random code, the random code is converted into the hash A hash value is calculated by applying the function as an input, and an exclusive OR operation between the random code and the identification code is performed to generate a t-bit operation code.

In this regard, as the first franchise store owner 11 corresponds to 'affiliate store owner 2' in Table 1, when the first identification number is '14592', the calculation unit 119 calculates the first identification number By performing a modulo-2 operation on each of the five constituting numbers '1', '4', '5', '9', and '2', '1', '0', '1', ' After generating result values such as 1' and '0', a 5-bit identification code of '10110' can be generated by configuring the resulting value as a bit string.

Then, the operation unit 119 randomly generates a 5-bit random code, such as '01110', applies the random code as an input to the hash function to calculate a hash value, and calculates the hash value, '01110' as the random code. A 5-bit operation code such as '11000' may be generated by performing an exclusive logical OR operation between '10110' and the identification code '10110'.

The transmission processing unit 120 encrypts the emotion analysis table with the hash value, and transmits the encrypted emotion analysis table and the operation code to the first electronic terminal 10 at the same time.

At this time, according to one embodiment of the present invention, the first electronic terminal 10 stores the first identification number and the hash function on a memory, and the encrypted emotion analysis table and When the operation code is received, a result value obtained by performing a modulo-2 operation on each of the t numbers constituting the first identification number stored in the memory is configured as a bit string, thereby obtaining t bits After generating the identification code of , the random code of t bits is restored by performing an exclusive OR operation between the operation code and the identification code, and when the random code is restored, storing the random code in the memory After applying the hash function as an input to calculate the hash value, the encrypted emotion analysis table may be decrypted based on the hash value and displayed on the screen.

In relation to this, as in the above-described example, when the first identification number is '14592' and the operation code is '11000', the first electronic terminal 10 receives the encrypted data from the service providing server 110. When the emotion analysis table and the operation code '11000' are received, the module for each of the five numbers '1', '4', '5', '9', and '2' constituting the first identification number By performing row-2 operation, result values such as '1', '0', '1', '1', '0' are generated, and then the result value is configured as a bit string, so that '10110' It is possible to generate the 5-bit identification code.

Then, the first electronic terminal 10 performs an exclusive OR operation between the operation code '11000' and the identification code '10110' received from the service providing server 110, so that the 5 The random code of bits can be restored.

In this way, when the random code is restored, the first electronic terminal 10 applies the random code as an input to the hash function stored in the memory of the first electronic terminal 10 to calculate the hash value, and then , the encrypted emotion analysis table can be decrypted with the hash value and displayed on the screen.

Through this, the first affiliated store owner 11 can confirm the emotion analysis result for customer feedback by checking the emotion analysis table displayed on the screen of the first electronic terminal 10, and improve the service quality based on this Or, by performing a certain customer marketing, you will be able to create higher profits.

2 is a flowchart illustrating an operating method of a service providing server providing an emotion analysis service for marketing according to an embodiment of the present invention.

In step S210, a dictionary database in which n preset (n is a natural number equal to or greater than 5) words (a preset order number is assigned to each of the n words) is stored.

In step S220, a reference vector storage unit in which a preset n-dimensional first reference vector corresponding to positive emotion information and a preset n-dimensional second reference vector corresponding to negative emotion information are stored. keep

In step S230, a plurality of sentences pre-collected as customer feedback on service quality are received from a first electronic terminal of a first affiliated store owner among a plurality of affiliated store owners subscribed to the emotion analysis service, and the plurality of sentences When a sentiment analysis request based on is received, for each of the plurality of sentences, after counting the frequency of each of the n words in each sentence, the frequency of each of the n words appears, A sentence vector corresponding to each of the plurality of sentences is generated by constructing an n-dimensional vector designated as a vector component according to the order assigned to each word.

In step S240, for each of the plurality of sentences, among the emotion information corresponding to the positive and the emotion information corresponding to the negative, the emotion having the reference vector having the greater cosine similarity with the sentence vector corresponding to each sentence Emotion information corresponding to each of the plurality of sentences is designated by confirming which information is the same.

In step S250, when emotion information corresponding to each of the plurality of sentences is designated, the emotion information corresponding to each of the plurality of sentences is transmitted to the first electronic terminal.

At this time, according to one embodiment of the present invention, in step S230, when the plurality of sentences and the emotion analysis request are received from the first electronic terminal, for each of the plurality of sentences, the n After preprocessing each of the plurality of sentences by removing text that does not match the number of words, by counting the frequency of each of the n words from the plurality of preprocessed sentences and constructing a vector, the plurality of sentences Sentence vectors corresponding to each of these can be created.

In addition, according to one embodiment of the present invention, in step S250, when emotion information corresponding to each of the plurality of sentences is designated, the emotion recorded by matching the plurality of sentences and the emotion information corresponding to each sentence to each other. After generating the analysis table, the emotion analysis table may be encrypted and transmitted to the first electronic terminal.

At this time, according to one embodiment of the present invention, in step S250, an identification number in which different identification numbers of t (t is a natural number of 2 or more) digits pre-issued for each of the plurality of affiliated store owners is stored. maintaining a hash function storage unit in which a hash function pre-shared with electronic terminals of each of the plurality of affiliate store owners is stored; when the emotion analysis table is generated, encrypting the emotion analysis table to Generating an encryption event to be transmitted to a first electronic terminal, when the encryption event occurs, checking a first identification number corresponding to the first affiliated store owner from the identification number storage unit, and obtaining the first identification number A t-bit identification code is generated by configuring the resultant value when the modulo-2 operation is performed on each of the constituting t numbers as a bit string, and a t-bit random code is randomly generated. Generating a t-bit operation code by applying a random code as an input to the hash function, calculating a hash value, and performing an exclusive OR operation between the random code and the identification code, and the sentiment analysis table using the hash value After encrypting, transmitting the operation code to the first electronic terminal at the same time as transmitting the encrypted emotion analysis table.

At this time, the first electronic terminal stores the first identification number and the hash function on a memory, and when the encrypted emotion analysis table and the operation code are received from the service providing server, they are stored on the memory After generating the identification code of t bits by configuring the resultant value of performing the modulo-2 operation on each of the t numbers constituting the first identification number as a bit string, the operation code and By performing an exclusive OR operation between the identification codes, the t-bit random code is restored, and when the random code is restored, the random code is applied as an input to the hash function stored in the memory to obtain the hash value After calculating , the encrypted emotion analysis table may be decrypted based on the hash value and displayed on the screen.

In the above, the operating method of the service providing server according to an embodiment of the present invention has been described with reference to FIG. 2 . Here, since the operation method of the service providing server according to an embodiment of the present invention may correspond to the configuration of the operation of the service providing server 110 described with reference to FIG. 1, a detailed description thereof will be omitted. .

A method of operating a service providing server according to an embodiment of the present invention may be implemented as a computer program stored in a storage medium for execution through a combination with a computer.

In addition, the operating method of the service providing server according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be specially designed and configured for the present invention, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

As described above, the present invention has been described by specific details such as specific components and limited embodiments and drawings, but these are provided to help a more general understanding of the present invention, and the present invention is not limited to the above embodiments. , Those skilled in the art in the field to which the present invention belongs can make various modifications and variations from these descriptions.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and it will be said that not only the claims to be described later, but also all modifications equivalent or equivalent to these claims belong to the scope of the present invention. .

110: service providing server
111: dictionary database 112: reference vector storage unit
113: Sentence vector generation unit 114: Emotion information storage unit
115: emotion information transmission unit 116: identification number storage unit
117: hash function storage unit 118: encryption event generating unit
119: calculation unit 120: transmission processing unit
10: first electronic terminal
11: First affiliate store owner

Claims (10)

In a service providing server that provides a sentiment analysis service for marketing,
a dictionary database in which preset n (n is a natural number of 5 or more) words, each of which is assigned a preset order number;
a reference vector storage unit for storing a preset n-dimensional first reference vector corresponding to positive emotion information and a preset n-dimensional second reference vector corresponding to negative emotion information;
When a plurality of sentences pre-collected as customer feedback on service quality are received from a first electronic terminal of a first affiliated store owner among a plurality of store owners subscribed to the sentiment analysis service, a request for sentiment analysis based on the plurality of sentences is received, for each of the plurality of sentences, after counting the frequency of each of the n words in each sentence, assigning the frequency of each of the n words to each of the n words a sentence vector generation unit configured to construct a sentence vector corresponding to each of the plurality of sentences by constructing an n-dimensional vector specified as a vector component according to the order in which the sentences are written;
For each of the plurality of sentences, among the emotion information corresponding to the positive and the emotion information corresponding to the negative, it is determined which emotion information has a reference vector having a greater cosine similarity with the sentence vector corresponding to each sentence. an emotion information specifying unit that designates emotion information corresponding to each of the plurality of sentences by doing so; and
If emotion information corresponding to each of the plurality of sentences is designated, an emotion information transmitting unit for transmitting emotion information corresponding to each of the plurality of sentences to the first electronic terminal.
A service providing server including a. According to claim 1,
The sentence vector generator
When the plurality of sentences and the emotion analysis request are received from the first electronic terminal, for each of the plurality of sentences, text that does not match the n words is removed from each sentence to obtain the plurality of sentences. After preprocessing each sentence, a sentence vector corresponding to each of the plurality of sentences is generated by counting the frequency of each of the n words from the preprocessed plurality of sentences and constructing a vector. server. According to claim 1,
The emotion information transmission unit
When emotion information corresponding to each of the plurality of sentences is designated, an emotion analysis table is generated in which the plurality of sentences and emotion information corresponding to each sentence are recorded in correspondence with each other, and then the emotion analysis table is encrypted to generate the first emotion analysis table. A service providing server characterized in that for transmission to an electronic terminal. According to claim 3,
The emotion information transmission unit
an identification number storage unit in which different identification numbers of t (t is a natural number of 2 or more) previously issued to each of the plurality of affiliated store owners are stored;
a hash function storage unit storing a hash function previously shared with electronic terminals of each of the plurality of affiliate store owners;
When the emotion analysis table is generated, an encryption event generating unit generating an encryption event for encrypting the emotion analysis table and transmitting the encrypted emotion analysis table to the first electronic terminal;
When the encryption event occurs, the first identification number corresponding to the first affiliate store owner is checked from the identification number storage unit, and each of the t numbers constituting the first identification number is modulo- 2 By composing the result value when performing the operation into a bit string, a t-bit identification code is generated, a t-bit random code is randomly generated, and then the random code is applied as an input to the hash function to generate a hash an operation unit generating a t-bit operation code by calculating a value and performing an exclusive OR operation between the random code and the identification code; and
After encrypting the emotion analysis table with the hash value, the transmission processing unit transmits the operation code while transmitting the encrypted emotion analysis table to the first electronic terminal.
including,
The first electronic terminal is
When the first identification number and the hash function are stored in a memory, and the encrypted emotion analysis table and the operation code are received from the service providing server, the first identification number stored in the memory is configured. After generating the identification code of t bits by configuring the resultant value of performing the modulo-2 operation on each of the t numbers as a bit string, an exclusive OR operation between the operation code and the identification code is performed. By performing this, the random code of t bits is restored, and when the random code is restored, the random code is applied as an input to the hash function stored in the memory to calculate the hash value, and then the hash value Service providing server, characterized in that for displaying on the screen by decrypting the encrypted emotion analysis table based on. In the operating method of a service providing server providing a sentiment analysis service for marketing,
maintaining a dictionary database in which preset n (n is a natural number of 5 or more) words, each of which is assigned a preset order number;
maintaining a reference vector storage unit storing a preset n-dimensional first reference vector corresponding to positive emotion information and a preset n-dimensional second reference vector corresponding to negative emotion information;
When a plurality of sentences pre-collected as customer feedback on service quality are received from a first electronic terminal of a first affiliated store owner among a plurality of store owners subscribed to the sentiment analysis service, a request for sentiment analysis based on the plurality of sentences is received, for each of the plurality of sentences, after counting the frequency of each of the n words in each sentence, assigning the frequency of each of the n words to each of the n words generating a sentence vector corresponding to each of the plurality of sentences by constructing an n-dimensional vector designated as a vector component according to the order in which the sentences are written;
For each of the plurality of sentences, among the emotion information corresponding to the positive and the emotion information corresponding to the negative, it is determined which emotion information has a reference vector having a greater cosine similarity with the sentence vector corresponding to each sentence. designating emotional information corresponding to each of the plurality of sentences by doing so; and
If emotion information corresponding to each of the plurality of sentences is designated, transmitting emotion information corresponding to each of the plurality of sentences to the first electronic terminal.
A method of operating a service providing server comprising a. According to claim 5,
The step of generating the sentence vector is
When the plurality of sentences and the emotion analysis request are received from the first electronic terminal, for each of the plurality of sentences, text that does not match the n words is removed from each sentence to obtain the plurality of sentences. After preprocessing each sentence, a sentence vector corresponding to each of the plurality of sentences is generated by counting the frequency of each of the n words from the preprocessed plurality of sentences and constructing a vector. How the server works. According to claim 5,
The step of transmitting to the first electronic terminal
When emotion information corresponding to each of the plurality of sentences is designated, an emotion analysis table is generated in which the plurality of sentences and emotion information corresponding to each sentence are recorded in correspondence with each other, and then the emotion analysis table is encrypted to generate the first emotion analysis table. A method of operating a service providing server, characterized in that for transmitting to an electronic terminal. According to claim 7,
The step of transmitting to the first electronic terminal
maintaining an identification number storage unit in which different identification numbers of t (t is a natural number of 2 or more) previously issued to each of the plurality of affiliated store owners are stored;
maintaining a hash function storage unit in which a hash function previously shared with an electronic terminal of each of the plurality of affiliate store owners is stored;
generating an encryption event for encrypting and transmitting the emotion analysis table to the first electronic terminal when the emotion analysis table is generated;
When the encryption event occurs, the first identification number corresponding to the first affiliate store owner is checked from the identification number storage unit, and each of the t numbers constituting the first identification number is modulo- 2 By composing the result value when performing the operation into a bit string, a t-bit identification code is generated, a t-bit random code is randomly generated, and then the random code is applied as an input to the hash function to generate a hash generating a t-bit operation code by calculating a value and performing an exclusive OR operation between the random code and the identification code; and
After encrypting the emotion analysis table with the hash value, transmitting the encrypted emotion analysis table and simultaneously transmitting the operation code to the first electronic terminal.
including,
The first electronic terminal is
When the first identification number and the hash function are stored in a memory, and the encrypted emotion analysis table and the operation code are received from the service providing server, the first identification number stored in the memory is configured. After generating the identification code of t bits by configuring the resultant value of performing the modulo-2 operation on each of the t numbers as a bit string, an exclusive OR operation between the operation code and the identification code is performed. By performing this, the random code of t bits is restored, and when the random code is restored, the random code is applied as an input to the hash function stored in the memory to calculate the hash value, and then the hash value Method of operating a service providing server, characterized in that for decrypting the encrypted emotion analysis table based on and displaying it on the screen. A computer-readable recording medium recording a computer program for executing the method of any one of claims 5 to 8 through a combination with a computer. A computer program stored in a storage medium for executing the method of any one of claims 5 to 8 through a combination with a computer.

Images