JP2019086940A - Relevant score calculating system, method and program - Google Patents

Abstract

To provide a relevant score calculating system capable of clarifying a relevance intensity between a person in an organization and a word.SOLUTION: A collecting unit 82 collects, from terminal devices, operation logs that are records of user operations to files. A word extracting unit 83 extracts a word from a file name described in each operation log. A relevant score calculating unit 84 calculates a relevant score that indicates a relevancy intensity between the user and the word on the basis of each operation log.SELECTED DRAWING: Figure 19

Description

  The present invention relates to an association score calculation system, an association score calculation method, and an association score calculation program for quantifying the strength of association between a person and a word.

  In Patent Document 1, an application log used by a user is determined by an operation log including information necessary to determine how much an application program installed in a personal computer or a portable information terminal is used. An information providing device is described. Further, Patent Document 1 also describes that the information providing apparatus determines how much the user uses the application program, and determines the knowledge level of the user for the application program.

  Patent Document 2 describes a human resource search system which performs registration, deletion, update, and the like of information on human resources in a profile database and refers to profile information to search for human resources matching a search keyword. Further, Patent Document 2 describes that by extracting keywords of a document in which a person is an author and obtaining high-order keywords, it is possible to obtain information on a specialized field or work of human resources.

JP, 2013-37584, A JP, 2005-327028, A

  It is preferable to be able to find people who are familiar with a particular field or technology or who have participated in a certain project within an organization such as a company. In addition, it is preferable to be able to easily know the field or technology that a person is familiar with, and the project that the person has participated in. However, in a large organization such as a large company, “who is familiar with which field and which technology” and “who has participated in which project” etc. has become knowledge that can not be understood without the organization for many years I will. In particular, such information as “who in the past has been familiar with which field and which technology” and “who participated in which project in the past” tends to be stronger. This makes it difficult for new employees and temporary workers to know who to ask what they want to hear. As a result, for example, the efficiency of product development may be reduced.

  Therefore, the inventors of the present invention thought that it would be preferable to be able to clarify the strength of association between a person in an organization and a word. If the inventors of the present invention can, for example, clarify the strength of the relationship between a certain person and the word "artificial intelligence", whether the person is familiar with the field or technology of "artificial intelligence" or not I thought it would be easy to estimate if I had participated in a project on "Artificial Intelligence".

  Therefore, the present invention aims to provide a relation score calculation system, a relation score calculation method, and a relation score calculation program capable of clarifying the strength of the relation between a person and a word in an organization.

  A related score calculation system according to the present invention includes: a collection unit that collects, from a terminal device, an operation log that is a record that a user operates a file; and a word extraction unit that extracts words from file names described in each operation log And a related score calculating unit configured to calculate a related score indicating the strength of the relation between the user and the word based on each operation log.

  In addition, the related score calculation system according to the present invention is described in a collection unit that collects schedule information describing a person, an event name, and a time zone in which the person is involved in an event having that event name; A word extraction unit for extracting a word from the event name, and an association score calculation unit for calculating an association score representing the degree of association between a person and a word based on each schedule information .

  Further, in the related score calculation method according to the present invention, an operation log, which is a record in which a user operates a file, is collected from a terminal device, words are extracted from file names described in each operation log, and each operation log is Based on the above, it is characterized by calculating a relevance score that represents the strength of the relevance between the user and the word.

  Further, in the related score calculation method according to the present invention, schedule information describing a person, an event name, and a time zone in which the person is involved in an event having the event name is collected and described in each schedule information. A word is extracted from an event name, and a relation score representing the strength of the relation between a person and a word is calculated based on each schedule information.

  Further, the related score calculation program according to the present invention causes a computer to collect, from a terminal device, an operation log which is a record of a file operated by a user, and extract words from file names described in each operation log. It is characterized in that a word extraction process and a relation score calculation process for calculating a relation score representing the degree of relation between a user and a word based on each operation log are executed.

  Further, the related score calculation program according to the present invention collects, on a computer, schedule information describing a person, an event name, and a time zone in which the person is involved in an event having the event name. Performing word extraction processing for extracting words from the event names described in the above, and related score calculation processing for calculating a related score representing the strength of the relation between a person and a word based on each schedule information It features.

  According to the present invention, it is possible to clarify the strength of association between people and words in an organization.

It is a block diagram showing an example of composition of a related score calculation system of a 1st embodiment of the present invention. It is a schematic diagram which shows the example of an operation log. It is a schematic diagram which shows the example of the related score calculated for every combination of a user and a word. It is a flowchart which shows the example of process progress of the related score calculation system of 1st Embodiment. It is a block diagram which shows the modification of 1st Embodiment. It is a schematic diagram which shows the example of the group of the user name memorize | stored in the memory | storage part, a word, and a related score. It is a block diagram which shows the structural example of the related score calculation system of the 2nd Embodiment of this invention. It is a schematic diagram which shows the example of a related score calculation result (set of the group of a user name, a word, and a related score). It is a schematic diagram which shows the example of a 1st table. It is a schematic diagram which shows the example of a 2nd table. It is a flowchart which shows the example of process progress of 2nd Embodiment. It is a flowchart which shows the example of the process which calculates the search score of a selection user and a keyword word. It is a flowchart which shows the example of the process which calculates the search score of score calculation object word and a keyword user name. It is a block diagram which shows the structural example of the related score calculation system of the 3rd Embodiment of this invention. It is a schematic diagram which shows the example of the screen which shows a clustering result. It is a block diagram which shows the structural example of the related score calculation system of 4th Embodiment. It is a schematic diagram which shows the example of schedule information. It is a schematic block diagram showing an example of composition of a computer concerning each embodiment of the present invention. It is a block diagram showing an outline of the present invention. It is a block diagram which shows the other example of the outline | summary of this invention.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

Embodiment 1
FIG. 1 is a block diagram showing an example of configuration of a relation score calculation system according to the first embodiment of this invention. However, FIG. 1 also illustrates an apparatus connected to the related score calculation system of the present invention via a communication network.

  A personal computer (hereinafter referred to as a PC) 91 is connected to the related score calculation system 1 of the present invention via the communication network 10.

  The PC 91 is used by, for example, a person belonging to an organization such as a company or a company. Each PC 91 is provided in one tissue. Hereinafter, the case where the organization is a company will be described as an example. However, the organization to which a person who uses the PC 91 belongs may not be a company or a company. Further, the organization may be an organization formed by a plurality of companies or the like, or may be a division of one company, a company or the like.

  Each PC 91 creates and stores one operation log related to the file by the user who operates the file. As described later, the operation log stored in each PC 91 is collected by the related score calculation system 1 (more specifically, the collection unit 2 of the related score calculation system 1).

  FIG. 2 is a schematic view showing an example of the operation log created by the PC 91. As shown in FIG. The operation log associates, for example, the file name, the user name of the user who operated the file, the content of the operation, and the date and time when the operation was performed (see FIG. 2). In FIG. 2, for convenience, the operation log numbers are also illustrated. FIG. 2 shows an example of the operation log, and the operation log is not limited to the example shown in FIG.

  The PC 91 describes a file name including a path name as a file name in the operation log.

  In addition, the PC 91 may determine the user name described in the operation log from, for example, an ID (Identification) used when the user logs in to the PC 91. However, the method of determining the user name by the PC 91 is not limited to this method.

  In each embodiment, a user name is used as a user ID (user identification information).

  Examples of the operation content described in the operation log include, for example, “file open”, “key touch”, “update (save)”, “file close” and the like. However, the contents of the operation described in the operation log are not limited to these, and may be “newly created” or the like.

  For example, if the user "Yamada" opens the file "/../artificial intelligence /../ A company's machine learning. Pptx" at 13:15 on October 10, 2017, the PC 91 will Create the first operation log illustrated in 2. Also, for example, when the user “Yamada” performs key touch (key input) on the file at 13:16 on October 10, 2017, the PC 91 is the second illustrated in FIG. Create an operation log of Also, for example, when the user “Yamada” updates (saves) the file at 15:17 on October 10, 2017, the PC 91 creates the m-1st operation log illustrated in FIG. 2. Do. Also, for example, when the user “Yamada” closes the file at 15:45 on October 10, 2017, the PC 91 creates the m-th operation log illustrated in FIG.

  The m + 1st to nth operation logs shown in FIG. 2 are examples of operation logs when the user "Yamada" operates another file "/../artificial intelligence //../ deep learning.docx". .

  Similarly, each PC 91 adds and stores an operation log each time the user performs an operation on a file.

  The association score calculation system 1 includes a collection unit 2, a word extraction unit 3, a score calculation unit 4, and a storage unit 5.

  The collecting unit 2 collects operation logs stored in each PC 91 from each PC 91. As shown in FIG. 2, each operation log includes a file name including a path name, and a user name of a user who used a file having the file name. Each operation log also includes information that can be derived as an association score, which is an index value indicating the strength of association between a user and a word. In the example illustrated in FIG. 2, the information described as “date and time” and “operation” corresponds to information that can derive a related score. However, the relevance score is not derived from one operation log, but is derived from a plurality of operation logs.

  The word extraction unit 3 performs morphological analysis on each file name (file name including path name) described in each operation log collected by the collection unit 2 to generate a file name including the path name. Extract the included words. However, the word extraction unit 3 does not redundantly extract the same word. For example, when the word "artificial intelligence" has already been extracted, the word extraction unit 3 ignores the word "artificial intelligence" extracted after the second time.

  For example, the word extraction unit 3 performs “artificial intelligence” by performing morphological analysis on a file name including a pathname “/ ··· / artificial intelligence / ···· company A machine learning .pptx, Extract words such as "A company" and "machine learning". In the following description, it is assumed that the company (organization) to which each user belongs is “company A”.

  Furthermore, for example, the word extraction unit 3 performs “morphointhmic analysis” by performing morphological analysis on a file name including a path name “/. Extract words such as "deep learning". However, as described above, since "artificial intelligence" has already been extracted, the word extraction unit 3 ignores the word "artificial intelligence" extracted here.

  The word extraction unit 3 obtains a set of words by performing the same processing on each file name described in each operation log. These words are different from one another.

  The score calculation unit 4 calculates, for each combination of each user who operated the file and each word extracted by the word extraction unit 3, a relation score which is an index value indicating the strength of the relation between the user and the word. The user is represented by a user name described in the operation log.

  In the second embodiment and the like of the present invention, an index value representing the strength of association between words is also used. In the present invention, an index value representing the degree of association between a user and a word is referred to as “association score”, and an index value representing the degree of association between words is referred to as “degree of association”. Distinguish values.

  The score calculation unit 4 calculates an association score for each combination of a user (user name) and a word, and causes the storage unit 5 to store a set of the user name, a word, and an association score.

  The storage unit 5 is a storage device that stores a set of a user (user name), a word, and a related score.

  There are a plurality of methods for calculating the relevance score. Hereinafter, three types of methods will be described as a method of calculating the relevance score. In any of the following three types of methods, the score calculation unit 4 calculates the association score for each combination of the user and the word, and causes the storage unit 5 to store the association score.

  The first calculation method is a relationship score between one user (hereinafter referred to as user U) and one word (hereinafter referred to as word W). Is the method of calculating the sum of the operation time of The longer the operation time, the stronger the association between the user U and the word W, and the shorter the operation time, the weaker the association between the user U and the word W is. Therefore, the operation time can be used as the association score.

  Here, first, the case where the actual reference time is treated as the operation time will be described as an example.

  The file name is a file name including a path name. Therefore, even if the word W is included in the path name, the word W is treated as being included in the file name. This point is the same in the second calculation method and the third calculation method described later.

  The actual reference time is the time when the window representing the contents of the file is active on the PC 91 (that is, the time when the window representing the contents of the file is displayed at the forefront from the user). is there.

  In the first calculation method of the association score, the score calculation unit 4 calculates the sum of the substantial reference time of the user U with respect to each file including the word W in the file name, and the summation is obtained by associating the user U with the word W Make it a score.

  If key touch has been performed, the window representing the contents of the file is active. Therefore, for example, the score calculation unit 4 determines, from the operation log, a state in which the key touch is continuously performed by the user U with respect to one file including the word W in the file name, and the first key touch time in that state The time from the last key touch time to the last key touch time is taken as the real reference time of the user U in the file.

  Furthermore, if a word W is included in the file name and there is another file operated by the user U, the score calculation unit 4 similarly calculates the substantial reference time for the file.

  Then, the score calculation unit 4 includes the word W in the file name, calculates the sum of the substantial reference times calculated for each file operated by the user U, and sets the sum as the association score between the user U and the word W.

  Further, if the start time and the end time in the active state are clearly indicated in the operation log, the score calculation unit 4 calculates the actual reference time based on those times explicitly indicated in the operation log. You may

  Further, the score calculation unit 4 may calculate the time from the file open to the file close as the operation time. In this case, the score calculation unit 4 includes the word W in the file name, calculates the time from the file open to the file close for each file operated by the user U, and adds the total of the time to the user U and the word W It may be a related score.

  Preferably, the substantial reference time is treated as the operation time.

  The second calculation method of the association score is a key touch when the user U operates each file including the word W in the file name as an association score of one user (user U) and one word (word W). It is a method of calculating the sum of the number of times. As the number of times of key touch increases, the amount of user U manipulating a file including the word W in the file name is increased. Therefore, it can be said that the association between the user U and the word W is strong as the number of key touches is large, and the association between the user U and the word W is weak as the number of key touches is small. Therefore, the number of key touches can be used as the association score.

  In the second calculation method, the score calculation unit 4 refers to the operation log and counts the number of times of key touch when the user U operates one file including the word W in the file name. Find the number of key touches in.

  Furthermore, if the file name includes the word W and there is another file operated by the user U, the score calculation unit 4 similarly obtains the number of key touches with respect to the file.

  Then, the score calculation unit 4 includes the word W in the file name, calculates the sum of the number of times of key touch calculated for each file operated by the user U, and sets the sum as the association score of the user U and the word W. .

The third calculation method of the association score is a method of computing the association score of one user (user U) and one word (word W) based on two ratios described next. Of the two proportions, one proportion is written as R ₁ and the other proportion is written as R ₂ .

R ₁ is, to the sum of the operation times of all the users in the organization for each file containing the word W in the file name, which is the ratio of the sum of the operation time of the user U for each file containing the word W in the file name. That is, R ₁ is represented by the formula (1) shown below.

When R ₂ focuses on individual words, the operation time of the user U for each file including the word W in the file name with respect to the total of the operation time of the user U for each file including the focused word in the file name The ratio of the sum of That is, R ₂ is represented by Formula (2) shown below.

The R ₁ will be described. The sum total of the operation time of the user U for each file including the word W in the file name (the numerator on the right side of the equation (1)) corresponds to the association score calculated by the first calculation method described above. That is, the score calculation unit 4 may calculate the sum of the operation time of the user U for each file including the word W in the file name by the method described in the first calculation method described above.

  The sum (the denominator on the right side of the right side of Formula (1)) of the operation time of all users in the organization for each file including the word W in the file name will be described. The score calculation unit 4 also calculates the sum of the operation time of the first user in the organization for each file including the word W in the file name by the method described in the first calculation method described above. Similarly, the score calculation unit 4 calculates the sum of the operation time of the second user in the organization for each file including the word in the W file name by the method described in the first calculation method described above. Similarly, the score calculation unit 4 calculates the sum of the user's operation time for each file including the word W in the file name for each person belonging to the organization. Furthermore, the score calculation unit 4 calculates the sum of “the sum of the user's operation time for each file including the word W in the file name” calculated for each person belonging to the organization. This value corresponds to the total operation time of all users in the organization for each file including the word W in the file name.

For example, it is assumed that the word W is "artificial intelligence" and the user U is "Yamada". In addition, it is assumed that 300 users exist in the organization "A company" to which Yamada belongs. In this case, the score calculation unit 4 obtains the sum of the operation time of the user "Yamada" for the file including the "artificial intelligence" in the file name as a numerator of the right side of Expression (1). In addition, the score calculation unit 4 calculates, for each of 300 individual users, the sum of the user's operation time for a file including “artificial intelligence” in the file name, and further calculates “operation for each individual user. The sum of “sum of time” is obtained as the denominator of the right side of equation (1). And the score calculation part 4 calculates R ₁ by Formula (1).

Next, R ₂ will be described. The numerator on the right side of Formula (2) is the same as the numerator on the right side of Formula (1). Therefore, the score calculation unit 4 may calculate the total sum of the operation time of the user U for each file including the word W in the file name by the method described in the first calculation method described above.

  The sum (the denominator on the right side of the right side of the equation (2)) of the operation time of the user U for each file including the focused word in the file name when focusing on each word will be described. The score calculation unit 4 focuses on the individual words extracted by the word extraction unit 3 (in other words, selects individual words one by one). Then, the score calculation unit 4 calculates the total of the operation time of the user U with respect to each file including the focused word (selected word) in the file name by the method described in the first calculation method described above. The score calculation unit 4 focuses on the next word (in other words, selects the next word), and sums up the operation time of the user U for each file including the focused word (selected word) in the file name. The calculation is performed by the method described in the first calculation method described above. As described above, the score calculation unit 4 calculates, for each word, the total sum of the operation time of the user U for each file including the word in the file name. Then, the score calculation unit 4 calculates the sum of "the sum of the operation time of the user U for each file including the word in the file name" calculated for each word. This value corresponds to the denominator on the right side of equation (2). The “sum of the operation time of the user U for each file including the focused word in the file name (the denominator on the right side of the equation (2)) when focusing on the individual word” is “each word includes the word It can be said that the total sum of the operation time of the user U for the file is the sum total of the total sum when the total sum is calculated for each word.

For example, as in the above-mentioned example, it is assumed that the word W is "artificial intelligence" and the user U is "Yamada". In this case, the score calculation unit 4 obtains the sum of the operation time of the user "Yamada" for the file including the "artificial intelligence" in the file name as the numerator of the right side of the equation (2). In addition, the score calculation unit 4 calculates, for each extracted word such as “artificial intelligence”, “company A”, “deep learning”, the sum total of the operation time of the user “Yamada” for the file including the word in the file name. calculate. Further, the sum of the “sum of operation times” calculated for each word is determined as the denominator on the right side of equation (2). Then, the score calculation unit 4 calculates R ₂ by equation (2).

After obtaining R ₁ and R ₂ , the score calculation unit 4 calculates the relation score between the user U and the word W by the following equation (3).

Related score = R ₁ × log (R ₂ ) (3)

  When the relevance score is calculated by this third calculation method, the value of the relevance score is low for words related to many people belonging to the organization, and for words related to a specific person belonging to the organization, The related score value is increased. For example, since each user belongs to company A, the word "company A" is considered to be associated with each user. However, it can be said that it is self-evident that the relationship between each user and the word "company A" is strong. Therefore, even if the word "A company" and the relevance score of each user are high, it does not make much sense, and it is preferable to lower the relevance score. In addition, when only a specific user belonging to an organization is associated with the word "artificial intelligence", it is preferable to increase the association score between the user and the word "artificial intelligence". In the third calculation method, the association score can be calculated as such.

  FIG. 3 is a schematic view showing an example of the association score calculated for each combination of the user and the word. The first association score shown in FIG. 3 is the association score calculated by the first calculation method. The second association score is an association score calculated by the second calculation method. The third association score is the association score calculated by the third calculation method. Although three types of association scores are illustrated in FIG. 3, the score calculation unit 4 may calculate any one type of association score. However, the score calculation unit 4 may calculate two or more types of association scores.

  As described above, the score calculation unit 4 calculates the association score for each combination of the user and the word, and stores the combination of the user name, the word, and the association score in the storage unit 5.

  The collection unit 2 is realized by, for example, a CPU (Central Processing Unit) of a computer that operates according to a related score calculation program and a communication interface of the computer. For example, the CPU may read the related score calculation program from a program storage medium such as a program storage device of a computer, and operate as the collection unit 2 using the communication interface according to the related score calculation program. Further, the word extraction unit 3 and the score calculation unit 4 are also realized by, for example, the CPU of the above-described computer that operates according to the related score calculation program. That is, as described above, the CPU reading the related score calculation program may operate as the word extraction unit 3 and the score calculation unit 4 according to the related score calculation program. The storage unit 5 is realized by the storage device of the computer described above. Also, the collecting unit 2, the word extracting unit 3 and the score calculating unit 4 may be realized by separate hardware.

  Further, the association score calculation system 1 may have a configuration in which two or more physically separated devices are connected by wire or wirelessly. This point is the same as in the other embodiments described later.

  Next, the process progress of the first embodiment will be described. FIG. 4 is a flowchart showing an example of the processing progress of the relevance score calculation system of the first embodiment. The detailed description of the items already described will be omitted.

  First, the collection unit 2 collects operation logs from each PC 91 provided in the company (step S1).

  Next, the word extraction unit 3 extracts words by performing morphological analysis on file names (file names including path names) described in each operation log (step S2).

  Next, based on each operation log, the score calculation unit 4 determines, for each combination of the user name described in the operation log and the word extracted in step S2, the user and the word represented by the user name. Calculate a relevance score that represents the strength of the relationship. Then, the score calculation unit 4 stores the combination of the user name, the word, and the related score in the storage unit 5 (step S3). The score calculation unit 4 may calculate the association score by any one of the first calculation method, the second calculation method, and the third calculation method described above.

  As a result, the storage unit 5 stores a plurality of sets of user names, words, and association scores.

  According to the present embodiment, the score calculation unit 4 calculates the relevance score for each combination of the user and the word based on each operation log. Then, in any of the first calculation method, the second calculation method, and the third calculation method described above, basically, the amount of operation of the user U with respect to the file including the word W in the file name (key touch The larger the number of times, the operation time, etc.), the larger the value of the association score. Therefore, the strength of the association between the user and the word is appropriately quantified for each combination of the user and the word. Thus, it is possible to clarify the strength of association between people in the organization and words.

  Next, a modification of the first embodiment will be described. FIG. 5 is a block diagram showing a modification of the first embodiment. The association score calculation system 1 shown in FIG. 5 includes, in addition to the collection unit 2, the word extraction unit 3, the score calculation unit 4 and the storage unit 5, a keyword reception unit 6, a search unit 7 and an output unit 8. About the element similar to the element shown in FIG. 1, the same code | symbol as FIG. 1 is attached | subjected, and description is abbreviate | omitted.

  In the following example, it is assumed that a plurality of pairs of user names, words, and related scores calculated by the above-described third calculation method are stored in the storage unit 5. FIG. 6 is a schematic view showing an example of a plurality of sets stored in the storage unit 5.

  The relevance score calculation system 1 illustrated in FIG. 5 receives a word as a search keyword, and searches for the user name of the user according to the word. Alternatively, the related score calculation system 1 accepts a user name as a search keyword, and searches for a word corresponding to the user name. Further, the relation score calculation system 1 may be capable of executing the above two types of searches.

  The keyword receiving unit 6 receives a search keyword from a searcher.

  The search unit 7 executes a search according to the search keyword.

  The output unit 8 outputs a search result.

  The keyword acceptance unit 6 accepts, for example, a search keyword from a terminal device (not shown) used by a searcher via a communication network, and the output unit 8 transmits a search result to the terminal device. do it. Hereinafter, a case where the keyword receiving unit 6 receives the search keyword as described above and the output unit 8 outputs the search result as described above will be described as an example. However, the reception mode of the search keyword and the output mode of the search result are not limited to this example. For example, the keyword receiving unit 6 may receive a search keyword via an input device (not shown) included in the related score calculation system 1. Further, the output unit 8 may output (display) the search result to a display device (not shown) included in the related score calculation system 1.

  The keyword acceptance unit 6 and the output unit 8 are realized by, for example, a CPU of a computer operating according to a related score calculation program and a communication interface of the computer, as the collecting unit 2 does. In addition, the search unit 7 is realized by the CPU of the computer that operates according to the related score calculation program. Also, the keyword acceptance unit 6, the search unit 7, the output unit 8 and other components may be realized by separate hardware.

  Next, an example of processing in which the related score calculation system 1 receives a word as a search keyword and searches for a user name of a user according to the word will be described.

  First, the keyword receiving unit 6 receives a word as a search keyword from the searcher.

  Next, among the sets of the user name, the word, and the related score stored in the storage unit 5, the search unit 7 relates to the word corresponding to the search keyword and the relation of a threshold (for example, 0.5) or more A set including a score is identified, and user names included in the set are identified as search results.

  For example, it is assumed that the keyword receiving unit 6 receives the word "artificial intelligence" as a search keyword. Further, it is assumed that the above threshold is 0.5. In this case, the search unit 7 specifies a set including the word “artificial intelligence” and a related score of 0.5 or more from the plurality of sets illustrated in FIG. In this example, the first set shown in FIG. 6 is identified. The search unit 7 obtains the user name “Yamada” included in the specified set as a search result. The output unit 8 outputs the search result. If there are a plurality of sets including the word “artificial intelligence” and a related score of 0.5 or more, the search unit 7 specifies all the sets, and searches the user name obtained from each set. I assume. Therefore, the user name obtained as the search result is not limited to one. The output unit 8 may arrange and output the plurality of user names obtained as the search result in the descending order of the related score.

  Thus, since the user name can be searched from the word, the searcher can easily know the user name of the user strongly involved in the field, technology, project, etc. indicated by the word designated as the search keyword.

  Next, an example of processing in which the related score calculation system 1 receives a user name as a keyword and searches for a word corresponding to the user name will be described.

  First, the keyword receiving unit 6 receives a user name as a search keyword from the searcher.

  Next, the search unit 7 stores the user name corresponding to the search keyword from among the combination of the user name, the word, and the relation score stored in the storage unit 5 and a threshold (for example, 0.5) or more. Identify a set that includes a relevance score, and identify words contained in the set as search results. At this time, if there are a plurality of sets including a user name corresponding to a search keyword and an association score equal to or higher than a threshold, the search unit 7 specifies all the sets and sets a word obtained from each set as a search result. Do. Therefore, the number of words obtained as a search result is not limited to one. The output unit 8 may arrange and output the plurality of words obtained as the search result in the descending order of the association score.

  For example, it is assumed that the keyword acceptance unit 6 accepts a user name "Yamada" as a search keyword. Further, it is assumed that the above threshold is 0.5. In this case, the search unit 7 specifies a user name “Yamada” and a set including a relevance score of 0.5 or more from the plurality of sets illustrated in FIG. In this example, the first, third and fourth sets shown in FIG. 6 are identified. The search unit 7 obtains a word included in each of the specified sets as a search result. That is, the search unit 7 obtains “artificial intelligence”, “machine learning” and “deep learning” as search results. The output unit 8 outputs the search result.

  As described above, since a word can be searched from a user name, a searcher can easily estimate a field, technology, etc. in which a person having a user name designated as a search keyword is familiar, or that the person participates It is possible to easily estimate a certain project etc.

  The above threshold "0.5" is an example, and the threshold may not be 0.5. The threshold may be determined according to the method of calculating the association score.

Embodiment 2
FIG. 7 is a block diagram showing an example of configuration of a relation score calculation system according to the second embodiment of this invention. About the component similar to the component shown to the related score calculation system (refer FIG. 1) of 1st Embodiment or the modification (refer FIG. 5) of 1st Embodiment, the code | symbol shown in FIG.1 and FIG.5 and The same reference numerals are given and the description is omitted.

  In the second embodiment, the association score calculation system 1 includes the collection unit 2, the word extraction unit 3, the score calculation unit 4, the storage unit 5, the first table generation unit 11, and the second table generation. A section 12, a keyword receiving section 6, a search section 17 and an output section 8 are provided.

  The collecting unit 2, the word extracting unit 3 and the score calculating unit 4 are the same as the respective elements shown in the first embodiment (see FIG. 1) or the modification of the first embodiment (see FIG. 5) is there.

  Further, the keyword accepting unit 6 and the output unit 8 are the same as the respective elements shown in the modification (see FIG. 5) of the first embodiment.

  The storage unit 5 is the same as the storage unit 5 in the first embodiment (see FIG. 1) or a modification of the first embodiment (see FIG. 5). However, in the present embodiment, the storage unit 5 not only stores a plurality of sets of user names, words, and association scores, but also stores a first table 21 and a second table 22 described later. Hereinafter, a set of sets of user names, words, and association scores (for example, a plurality of sets illustrated in FIG. 6) which the score calculation unit 4 stores in the storage unit 5 will be referred to as association score calculation results 20.

  Further, in the present embodiment, a case where the score calculation unit 4 calculates the relevance score by the above-described third calculation method will be described as an example. However, the score calculation unit 4 may calculate the relevance score by the first calculation method or the second calculation method described above.

  In the following description, it is assumed that the score calculation unit 4 has already calculated the relevance score and stores the relevance score calculation result 20 in the storage unit 5. FIG. 8 is a schematic view showing an example of the association score calculation result 20 (a set of a set of a user name, a word and an association score). Here, the case where the related score calculation result 20 illustrated in FIG. 8 is stored in the storage unit 5 will be described as an example.

  The first table generation unit 11 generates the first table 21 based on the association score calculation result 20 and causes the storage unit 5 to store the first table 21. The first table 21 is a table in which relationships among user IDs, words, and association scores are described. More specifically, the first table 21 arranges the user names included in the related score calculation result 20 on one of the vertical axis and the horizontal axis, and is included in the related score calculation result 20. A word is arranged on the other axis, and it is a table in which the user having the user name and the relevance score of the word are described in the column where the user name and the word intersect.

  In this example, when generating the first table, the first table generation unit 11 arranges the user names on the vertical axis and arranges the words on the horizontal axis as an example. The generation unit 11 may arrange the user names on the horizontal axis and arrange the words on the vertical axis.

  Further, when arranging the user names along the axis, the first table generation unit 11 arranges the user names of the same user without overlapping. For example, in the association score calculation result 20 shown in FIG. 8, the user name “Yamada” is included in the first set, and the user name “Yamada” is included in the second set. This user name "Yamada" is the user name of the same user. Therefore, the first table generation unit 11 may arrange the user name "Yamada" once when arranging the user names along the axis.

  Similarly, when arranging the words along the axis, the first table generation unit 11 arranges the same words without overlapping. For example, in the association score calculation result 20 shown in FIG. 8, the word "artificial intelligence" is included in a plurality of sets. However, when arranging the words along the axis, the first table generation unit 11 may arrange the word “artificial intelligence” once.

  An example of the first table generated by the first table generation unit 11 is shown in FIG. The first table generation unit 11 arranges user names (“Yamada”, “Suzuki”, “Tanaka”, etc.) included in the related score calculation result 20 along the direction of the vertical axis (see FIG. 9). . In addition, the first table generation unit 11 measures the words included in the related score calculation result 20 (“artificial intelligence”, “A company”, “machine learning”, “deep learning”, etc.) along the horizontal axis. (See Fig. 9).

  Then, the first table generation unit 11 describes the association score of the user having the user name and the word in a field where the user name and the word intersect. For example, in the example shown in FIG. 8, the association score between the user name “Yamada” and the word “artificial intelligence” is “0.80”. Therefore, the first table generation unit 11 writes “0.80” in the column where “Yamada” and “Artificial intelligence” intersect in the first table 21 (see FIG. 9). Further, for example, in the example illustrated in FIG. 8, the association score between the user name “Yamada” and the word “company A” is “0.10”. Therefore, the first table generation unit 11 describes “0.10” in the column where “Yamada” and “A company” intersect in the first table 21. The first table generation unit 11 similarly describes the association score for each field where the user name and the word intersect.

  The first table generation unit 11 stores the first table 21 generated as described above in the storage unit 5.

  The second table generation unit 12 generates the second table 22 based on the first table 21 and stores the second table 22 in the storage unit 5. The second table is a table describing the degree of association representing the degree of association between words calculated based on the first table. More specifically, in the second table 22, words are arranged on both the vertical axis and the horizontal axis, and in the field where the words intersect, the relationship between the words calculated based on the first table 21 is strong Is a table describing the degree of association representing As described above, in the present invention, an index value representing the strength of association between a user and a word is referred to as a “association score”, and an index value representing the strength of association between words is referred to as a “degree of association”. Distinguish between two types of index values.

  FIG. 10 is a schematic view showing an example of the second table. In this example, the case where the second table generation unit 12 arranges words on the vertical axis and the horizontal axis in the same order as the first table 21 will be described as an example. For example, in the first table illustrated in FIG. 9, words are arranged in the order of “artificial intelligence”, “company A”, “machine learning”, “deep learning”,. The second table generation unit 12 arranges the words in the same order as the order in each of the vertical axis and the horizontal axis of the second table (see FIG. 10).

  Then, the second table generation unit 12 calculates, for each combination of one word and one word, a degree of association representing the degree of association between the words, and in a field where the words intersect, Describe the degree of association. The second table generation unit 12 also calculates the degree of association with respect to the same words. For example, the second table generation unit 12 also calculates the degree of association between “artificial intelligence” and “artificial intelligence”.

  Here, the degree of association between words will be described. First, in the first table 21 illustrated in FIG. 9, the case of focusing on two words “artificial intelligence” and “machine learning” will be described.

  The “artificial intelligence” and the related score of each user are arranged in the order of the user name in the first table 21 as follows.

  0.80, 0.20, 0.60, 0.43, ...

  Moreover, if "machine learning" and the related score of each user are arranged in order of the user name in the first table 21, it will be as follows.

  0.79, 0.22, 0.58, 0.45, ...

  It can be said that the tendency of the change of the relation score in the above-mentioned line of the relation score is similar. In this case, the degree of association between "artificial intelligence" and "machine learning" is high.

  Next, the case of focusing on two words "artificial intelligence" and "company A" will be described.

  As described above, the “artificial intelligence” and the related score of each user are arranged in the order of the user name in the first table 21 as follows.

  0.80, 0.20, 0.60, 0.43, ...

  In addition, when “A company” and the related score of each user are arranged in the order of the user name in the first table 21, it becomes as follows.

  0.10, 0.40, 0.35, 0.05, ...

    It can be said that the tendency of the change of the relation score in the above-mentioned line of the relation score is not similar. In this case, the degree of association between "artificial intelligence" and "company A" is low.

The second table generation unit 12 may calculate the correlation coefficient between the words as the degree of association between the words. Here, as relevance of a word w ₁ and word w _2, it will be described for calculating a correlation coefficient of words w ₁ and word w _2. More specifically, the correlation coefficient between the word w ₁ and the word w ₂ is a correlation function of the alignment of the word w ₁ and the related score of each individual user, and the alignment of the word w ₂ and the related score of each individual user is there.

  An arrangement of association scores (numerical values) in the case where the association scores of one word and each user are arranged in the order of user names in the first table 21 is referred to as a series of the words. For example, in the example shown in FIG. 9, the sequence of "artificial intelligence" is as follows.

  0.80, 0.20, 0.60, 0.43, ...

It is assumed that the sequence of the word w ₁ is (x ₁ , x ₂ ,..., X _n ). And let this sequence be x. Note that in the example shown in FIG. 9, the word sequence is obtained by arranging numerical values in the vertical direction, but here, for convenience, horizontal lines such as (x ₁ , x ₂ ,..., X _n ) Show it side by side. This is also true for the word w ₂ described next.

Also, assume that the sequence of the word w ₂ is (y ₁ , y ₂ ,..., Y _n ). And let this sequence be y.

  As described above, let n be the number of association scores belonging to the series.

The second table generation unit 12 may calculate the correlation coefficient between x and y as the degree of association between the word w ₁ and the word w ₂ . Let r be the correlation coefficient between x and y. The second table generation unit 12 calculates the correlation coefficient r between x and y by the calculation of Equation (4) shown below.

In equation (4), s _xy is the covariance of x and y. Also, s _x is the standard deviation of x, and s _y is the standard deviation of y. x _i is the ith association score at x. y _i is the ith association score at y.

は、ｘの平均値である。

Is the average value of x.

は、ｙの平均値である。

Is the average value of y.

  The second table generation unit 12 calculates a correlation coefficient by calculation of equation (4) for each combination of one word and one word, and uses the correlation coefficient as a degree of association to calculate a second table. Described in 22. When the two words forming a combination are different words, the degree of association between the two words is described in two places in the second table 22. For example, in the example shown in FIG. 10, the degree of association between “Artificial Intelligence” and “Company A” is described in the first row, the second column, and the second row, the first column.

  The second table generation unit 12 stores the second table 22 generated as described above in the storage unit 5.

  The relevance score calculation system 1 of the second embodiment receives a word as a search keyword, and searches for a user name of a user according to the word. Alternatively, the relevance score calculation system 1 according to the second embodiment receives a user name as a search keyword, and searches for a word corresponding to the user name. In addition, the relation score calculation system 1 of the second embodiment may be capable of executing the two types of searches described above.

  When searching for the user name of the user according to the word designated by the searcher, the keyword receiving unit 6 receives a word from the searcher as a search keyword. Then, based on the first table 21 and the second table 22, the search unit 17 searches for a user name corresponding to the word corresponding to the search keyword.

  Further, when searching for a word corresponding to the user name designated by the searcher, the keyword receiving unit 6 receives the user name from the searcher as a search keyword. Then, the search unit 17 searches for a word corresponding to the user name corresponding to the search keyword based on the first table 21 and the second table 22.

  In the second embodiment, the collection unit 2, the keyword reception unit 6, and the output unit 8 are realized by a CPU of a computer operating according to a related score calculation program and a communication interface of the computer. For example, the CPU reads a related score calculation program from a program storage medium such as a program storage device of a computer and operates as the collection unit 2, the keyword reception unit 6, and the output unit 8 using a communication interface according to the related score calculation program. Just do it. In addition, the word extraction unit 3, the score calculation unit 4, the first table generation unit 11, the second table generation unit 12 and the search unit 17 are also realized by, for example, the CPU of the above computer operating according to the related score calculation program. Ru. That is, as described above, the CPU reading the related score calculation program executes the word extraction unit 3, the score calculation unit 4, the first table generation unit 11, the second table generation unit 12, and the search according to the related score calculation program. It may operate as the unit 17. Further, the collecting unit 2, the keyword receiving unit 6, the output unit 8, the word extracting unit 3, the score calculating unit 4, the first table generating unit 11, the second table generating unit 12 and the searching unit 17 are different hardwares. It may be realized by

  FIG. 11 is a flowchart showing an example of the process progress of the second embodiment. A detailed description of the same operation as the operation described in the first embodiment and the operation already described in the second embodiment will be omitted.

  Steps S1 to S3 are the same as steps S1 to S3 (see FIG. 4) in the first embodiment, and the description will be omitted.

  After step S3, the first table generation unit 11 generates the first table 21 (see FIG. 9) based on the association score calculation result 20, and stores the first table 21 in the storage unit 5. (Step S4). The operation of generating the first table 21 has already been described, so the description is omitted here.

  Next, the second table generation unit 12 generates the second table 22 (see FIG. 10) based on the first table 21 and stores the second table 22 in the storage unit 5 (step S5). ). The operation of generating the second table 22 has also been described, so the description is omitted here.

  After the first table 21 and the second table 22 are generated, the keyword receiving unit 6 receives a search keyword from the searcher (step S6). The keyword receiving unit 6 may receive a word as a search keyword. The keyword accepting unit 6 may accept a user name as a search keyword.

  Next, the search unit 17 obtains a search result according to the search keyword based on the first table 21 and the second table 22 (step S7). When the search keyword is a word, the search unit 17 searches for a user name corresponding to the word based on the first table 21 and the second table 22. When the search keyword is a user name, the search unit 17 searches for a word corresponding to the user name based on the first table 21 and the second table 22. Details of the operation of step S7 will be described later.

  After step S7, the output unit 8 outputs the search result (step S8). The mode in which the output unit 8 outputs the search result is the same as that of the modification of the first embodiment.

  Next, the operation of step S7 will be described. First, in step S6, the case where the keyword receiving unit 6 receives a word as a selected keyword, and the searching unit 17 searches for a user name corresponding to the word will be described. Hereinafter, the word corresponding to the search keyword is referred to as a keyword word.

  The search unit 17 sequentially selects individual user names and calculates search scores of the selected user names (hereinafter, referred to as selected user names) and keyword words. The search score is an index value indicating the strength of the association between the user having the selected user name and the word, but is calculated using the association score described above, and the calculation method is different from that of the association score. Therefore, in the following description, the term search score is used to distinguish it from the related score.

  It is assumed that the search unit 17 selects one selected user name. An operation in which the search unit 17 calculates the search score of the selected user name and the keyword word will be described. FIG. 12 is a flowchart showing an example of processing for calculating search scores of the selected user and the keyword word.

  First, the search unit 17 initializes the value of the search score of the selected user name to 0 (step S11).

  Next, the search unit 17 selects one word not yet selected in step S12 from the words arranged in the axis of the first table (may be the axis of the second table) (step S12). S12). The word selected in step S12 is hereinafter referred to as a selected word. The selected word may be identical to the keyword word.

  Next, the search unit 17 calculates the product of the degree of association between the keyword word and the selected word, and the selected user name and the related score of the selected word (step S13). The search unit 17 may read the degree of association used in step S13 from the second table, and read the association score used in step S13 from the first table.

  Next, the search unit 17 adds the product calculated in step S13 to the search score (step S14).

  Next, the search unit 17 determines whether there is a word not selected in step S12 (step S15). If there is an unselected word (Yes in step S15), the search unit 17 repeats the process from step S12.

  When there is no unselected word (No in step S15), the search unit 17 determines the value of the search score at that time as the search score of the selected user name and the keyword word, and ends the process.

  The above search score calculation process can be expressed by the following equation (5).

  In equation (5), the word i means the i-th selected word selected.

  For example, it is assumed that the first table 21 shown in FIG. 9 and the second table 22 shown in FIG. 10 are stored in the storage unit 5. Then, it is assumed that the keyword word (word corresponding to the search keyword) is "artificial intelligence" and the selected user name is "Yamada". In this case, the search unit 17 calculates the search score of the selected user name “Yamada” and the keyword word “artificial intelligence” according to the following equation (see FIGS. 9 and 10).

  Search score = 1.00 × 0.80 + 0.07 × 0.10 + 0.87 × 0.79 + 0.79 × 0.82 + ···

  Further, it is assumed that the selected user name is "Suzuki". In this case, the search unit 17 calculates the search score of the selected user name “Suzuki” and the keyword word “artificial intelligence” according to the following equation (see FIGS. 9 and 10).

  Search score = 1.00 × 0.20 + 0.07 × 0.40 + 0.87 × 0.22 + 0.79 × 0.18 +

  The search unit 17 obtains a search score for each of the user names described in the first table 21 by the above process. Then, the search unit 17 obtains a user name whose search score is equal to or more than a threshold as a search result. Therefore, there can be a plurality of user names obtained as search results. The output unit 8 outputs the user name obtained as the search result. The output unit 8 may arrange and output a plurality of user names obtained as a search result in the descending order of the search score.

  This search method also uses a second table indicating the degree of association between words. Therefore, the user name of the user who is strongly associated with another word that is highly associated with the word specified by the searcher as the search keyword can be obtained as the search result.

  For example, in a company to which each user belongs, "Red Rockets" and "Green Rockets" are product names of important products, and the relationship between the two products is strong. In this case, according to the above search method, even if "Red Rockets" is used as a search keyword, not only the user name of a user strongly associated with "Red Rockets" but also "Red Rockets" The user name of a user strongly associated with a certain "Green Rockets" can also be obtained as a search result. Therefore, the user name can be widely searched based on the word designated by the searcher as the search keyword.

  Further, in the present embodiment, the second table is generated using the words included in the operation log collected from the PC 91 provided in the company. Therefore, the second table can include words frequently used by the company such as “Red Rockets” and “Green Rockets” as exemplified above. In the case where the first table and the second table are created manually, not only it takes a lot of time and effort, but words and the like used uniquely by the organization are easily leaked from the first table and the second table. Therefore, it is possible to easily create the first table and the second table without leaking the word used uniquely by the organization, and further, as described above, based on the word specified as the search keyword, the user name can be widely used. It can be searched.

  Next, in step S6, a case will be described in which the keyword receiving unit 6 receives a user name as a selected keyword, and the searching unit 17 searches for a word corresponding to the user name. Hereinafter, the user name corresponding to the search keyword is referred to as a keyword user name.

  The search unit 17 sequentially selects individual words and calculates a search score of the selected word and the keyword user name. This selected word is referred to as a score calculation target word. Also, even after one score calculation target word is selected, words are sequentially selected separately as described later (see step S22 in FIG. 13 described later). The word selected in step S22 described later is referred to as a selected word.

  It is assumed that the search unit 17 selects one score calculation target word. Below, the operation | movement which the search part 17 calculates the search score of a score calculation object word and a keyword user name is demonstrated. FIG. 13 is a flowchart showing an example of processing for calculating search scores of score calculation target words and keyword user names.

  First, the search unit 17 initializes the search score value of the score calculation target word to 0 (step S21).

  Next, the search unit 17 selects one word not yet selected in step S22 from the words arranged on the axis of the first table (may be the axis of the second table) (step S22) S22). As described above, the word selected in step S22 is referred to as a selected word. The selected word may be identical to the score calculation target word.

  Next, the search unit 17 calculates the product of the association score between the keyword user name and the selected word, and the score calculation target word and the degree of association of the selected word (step S23). The search unit 17 may read the association score used in step S23 from the first table, and read the association degree used in step S23 from the second table.

  Next, the search unit 17 adds the product calculated in step S23 to the search score (step S24).

  Next, the search unit 17 determines whether there is a word not selected in step S22 (step S25). If there is an unselected word (Yes in step S25), the search unit 17 repeats the process from step S22.

  When there is no unselected word (No in step S25), the search unit 17 determines the value of the search score at that time as the search score of the score calculation target word and the keyword user name, and ends the processing.

  The above search score calculation process can be expressed by the following equation (6).

  In equation (6), the word i means the i-th selected word selected.

  For example, it is assumed that the first table 21 shown in FIG. 9 and the second table 22 shown in FIG. 10 are stored in the storage unit 5. Then, it is assumed that the keyword user name (user name corresponding to the search keyword) is "Yamada" and the score calculation target word is "artificial intelligence". In this case, the search unit 17 calculates the search score of the score calculation target word “artificial intelligence” and the keyword user name “Yamada” according to the following equation (see FIGS. 9 and 10).

  Search score = 0.08 x 1.00 + 0.10 x 0.07 + 0.79 x 0.87 + 0.82 x 0.79 + ...

  Further, it is assumed that the score calculation target word is “A company”. In this case, the search unit 17 calculates a search score for the score calculation target word “company A” and the keyword user name “Yamada” according to the following equation (see FIGS. 9 and 10).

  Search score = 0.08 × 0.07 + 0.10 × 1.00 + 0.79 × 0.09 + 0.82 × 0.11 + ···

  The search unit 17 obtains a search score by the above process for each of the score calculation target words to be sequentially selected. Then, the search unit 17 obtains a word whose search score is equal to or more than a threshold as a search result. Therefore, there can be a plurality of words obtained as search results. The output unit 8 outputs the word obtained as the search result. The output unit 8 may arrange and output a plurality of words obtained as a search result in the descending order of the search score.

  Also in the search method for searching for words from user names as described above, a second table indicating the degree of association between words is also used. Therefore, not only the word having a high degree of association with the user name indicated by the keyword user name designated by the searcher, but also another word having a high degree of association with the word can be obtained as a search result.

  For example, as in the above-mentioned example, in the company to which each user belongs, "Red Rockets" and "Green Rockets" are product names of important products, and the relationship between the two products is strong. Then, it is assumed that the association between the user "Yamada" and the word "Red Rockets" is strong. In this case, when the searcher designates "Yamada" as the keyword user name, not only the word "Red Rockets" strongly related to "Yamada" but also "Green Rockets" strongly related to the word "Red Rockets" Can be obtained as Because the relationship between "Red Rockets" and "Green Rockets" is strong, "Yamada", which has a strong relationship with "Red Rockets", is considered to be strongly related to "Green Rockets". According to the above method, it is possible to widely search for words that are considered to be strongly related to the user indicated by the user name designated as the search keyword.

  Also, as described above, it is possible to easily create the first table and the second table without leaking the words used uniquely by the organization.

  As described above, in the present embodiment, when the keyword receiving unit 6 receives a word as a selected keyword and the searching unit 17 searches for a user name corresponding to the word, the user name can be widely searched. When the keyword acceptance unit 6 accepts a user name as a selected keyword and the search unit 17 searches for a word corresponding to the user name, the word can be widely searched. In addition, the first table and the second table can be easily created without leaking words used unique to the organization.

Embodiment 3
FIG. 14 is a block diagram showing an example of configuration of a relation score calculation system according to the third exemplary embodiment of the present invention. The association score calculation system of the third embodiment further includes a clustering unit 31, a cluster output unit 32, and an exclusion target word in addition to the components included in the association score calculation system (see FIG. 7) of the second embodiment. And a reception unit 33. In FIG. 14, elements similar to the elements shown in FIG. 7 are assigned the same reference numerals as in FIG. Each of the first table generation unit 11 and the second table generation unit 12 performs an operation described later in addition to the operation described in the second embodiment.

  The clustering unit 31 reads the second table 22 (see, for example, FIG. 10) from the storage unit 5 and, based on the second table 22, performs clustering on the words described in the second table 22. Do. The clustering unit 31 performs clustering on the words by a clustering method such as a k-means method or a hierarchical clustering algorithm, for example. In a clustering method such as the k-means method or hierarchical clustering algorithm, clustering can be performed on words aligned on the axis of the second table 22 using the second table 22 as input data. The clustering unit 31 assigns, for example, a cluster number as cluster identification information to each cluster, and causes the storage unit 5 to store the relationship between a cluster and a word belonging to the cluster as a clustering result 23.

  The cluster output unit 32 receives, for example, an output request of a clustering result from a terminal device (not shown) of a manager of the related score calculation system 1 (hereinafter simply referred to as a manager) via a communication network. In response to the output request, the screen information of the screen showing the clustering result is transmitted to the terminal device (not shown). FIG. 15 is a schematic view showing an example of a screen showing a clustering result. On the screen showing the clustering result, for example, a cluster number and each word belonging to the cluster are displayed for each cluster. Further, a check box 41 is displayed together with each cluster number and each word. As shown in FIG. 15, the number of words belonging to each cluster may be different. Further, the screen showing the clustering result includes a confirmation button 42.

  When the cluster output unit 32 receives an output request of the clustering result from the administrator's terminal device via the communication network, the cluster output unit 32 reads the clustering result 23 from the storage unit 5. Then, the cluster output unit 32 displays the cluster number and the word belonging to the cluster indicated by the cluster number based on the clustering result 23, and displays the check box 41 together with each cluster number and each word, and further, Screen information of a screen (for example, the screen illustrated in FIG. 15) including the determination button 42 is generated. Then, the cluster output unit 32 transmits the screen information to the terminal device of the administrator via the communication network.

  When the terminal device of the administrator receives the screen information from the cluster output unit 32, the terminal device displays, for example, a screen illustrated in FIG. 15 based on the screen information.

  The administrator checks the screen illustrated in FIG. 15 (the screen displaying the clustering result of words), and puts a check in the check box 41 corresponding to the word that the administrator has judged to be excluded. When the administrator determines that all words belonging to one cluster should be excluded, the administrator puts a check in the check box 41 corresponding to that cluster. Checking that the check box 41 corresponding to a word is checked means that it is determined that the word should be excluded. Further, that the check box 41 corresponding to a cluster is checked means that it has been determined that all words belonging to that cluster should be excluded. Here, "to be excluded" means that words should be excluded from words aligned on the horizontal axis of the first table and each axis of the second table.

  The confirmation button 42 is a button for inputting that the determination as to whether to exclude each word is completed. When the administrator clicks the confirmation button 42, the terminal device of the administrator determines the words that the administrator has judged to be excluded according to which check box 41 is checked, and the administrator determines by the administrator The word determined to be excluded is sent to the relevance score calculation system 1.

  The exclusion target word reception unit 33 of the related score calculation system 1 receives, via the communication network, a word (a word determined to be excluded by the administrator) transmitted by the terminal device of the administrator. The number of words received by the exclusion target word reception unit 33 is not limited to one. It can be said that the exclusion target word reception unit 33 receives specification of a word to be excluded from the words aligned on the horizontal axis of the first table and each axis of the second table.

  The exclusion target word reception unit 33 notifies the first table generation unit 11 of the word (word to be excluded) received from the terminal device of the administrator. When receiving the notification of the word, the first table generation unit 11 excludes the notified word from the words already arranged along the horizontal axis of the first table 21, and the first table 21 is again read. Generate Then, the first table generation unit 11 replaces the first table 21 stored in the storage unit 5 with the first table 21 generated again.

  When the first table generation unit 11 generates the first table 21 again, the second table generation unit 12 generates the second table again based on the newly generated first table 21. At this time, the second table generation unit 12 generates the second table by excluding the words received by the exclusion target word reception unit 33 from the words aligned on each axis. Then, the second table generation unit 12 replaces the second table 22 stored in the storage unit 5 with the second table 22 generated again.

  The operation of regenerating the first table 21 and the operation of recreating the second table 22 are the same as in the first embodiment described in the second embodiment except that the number of words aligned on the axis is reduced. The operation of generating the table 21 and the operation of generating the second table 22 are the same.

  The cluster output unit 32 and the exclusion target word reception unit 33 are realized by, for example, a CPU of a computer operating according to the related score calculation program and a communication interface of the computer. In addition, the clustering unit 31 is realized by the CPU of the computer that operates according to the related score calculation program.

  According to this embodiment, it is possible to exclude from the first table and the second table the words determined by the administrator to be excluded from the first table and the second table. As a result, for example, when searching for a word using the user name as a search keyword, it is possible to prevent the word designated as the word to be excluded by the administrator from being included in the search result.

  An example of a word judged by the administrator to be excluded will be described. For example, the user name "Yamada" may be included in the file name newly created or browsed. In that case, when searching for a word using the user name "Yamada" as a search keyword, the search result may include the word "Yamada". However, when searching for a word using the user name “Yamada” as a search keyword, even if the search result includes the word “Yamada”, it does not make much sense to the searcher.

  Therefore, for example, when the screen illustrated in FIG. 15 is displayed, the administrator determines that the word “Yamada” considered to be the same character string as the user name should obviously be excluded. The check box 41 corresponding to the word “Yamada” shown in FIG. As a result, the first table generation unit 11 generates a new first table in which “Yamada” is excluded from the word alignment on the horizontal axis. Subsequently, the second table generation unit 12 generates a new second table in which “Yamada” is excluded from the word arrangement of each of the vertical axis and the horizontal axis. As a result, for example, when searching for a word using the user name "Yamada" as a search keyword, it is possible to prevent the word "Yamada" from being included in the search result.

  In addition, the cluster output part 32 may display the screen which shows a clustering result on the display apparatus (not shown) with which the related score calculation system 1 is provided. In addition, the exclusion target word accepting unit 33 is operated by an input device (not shown) included in the related score calculation system 1 on the screen displayed on the display device (input of a check to the check box 41, and the confirmation button 42 And the designation of a word to be excluded may be accepted according to the operation.

Embodiment 4
In the first to third embodiments, the collection unit 2 collects operation logs, the word extraction unit 3 extracts words from each file name described in each operation log, and the score calculation unit 4 However, the case of calculating the relevance score for each combination of each user who operated the file and each extracted word was shown.

  In the fourth embodiment, the case where the collection unit collects not the file operation log but schedule information is described as an example.

  FIG. 16 is a block diagram showing an example of configuration of a relation score calculation system according to the fourth embodiment. In the related score calculation system 1 shown in FIG. 16, the collection unit 2, the word extraction unit 3 and the score calculation unit 4 in the first embodiment are replaced with a collection unit 52, a word extraction unit 53 and a score calculation unit 54. is there. The storage unit 5 is the same as the storage unit 5 in the first embodiment.

  Further, the association score calculation system 1 shown in FIG. 16 is connected via the communication network 10 to a schedule management server 61 that holds schedule information of each person belonging to the organization.

  The collection unit 52 collects, from the schedule management server 61, schedule information of each person belonging to the organization, which is stored in the schedule management server 61. The schedule information may be stored in each PC (not shown in FIG. 16). In this case, the collection unit 52 may collect schedule information of each person belonging to the organization from the individual PC.

  Hereinafter, identification information of a person belonging to an organization is referred to as person identification information. Moreover, as person identification information, the case where names of persons, such as "Yamada" are used, is demonstrated as an example.

  FIG. 17 is a schematic view showing an example of schedule information. The schedule information is described, for example, in association with person identification information of a person belonging to an organization, an event name, and a time zone in which the person is involved in an event having that event name, as illustrated in FIG. . The time zone is represented by the start date and time and the end date and time.

  The first schedule information shown in FIG. 17 is that the person "Yamada" was involved in the "Artificial Intelligence Development Conference" from 10:00 on August 17, 2017 to 12:00 on the same day (in other words, he attended) It represents that. Hereinafter, the time when a person is involved in an event will be referred to as an event participation time. The event participation time for one event is a time obtained by subtracting the start date and time from the end date and time described in association with the event.

  The word extraction unit 53 extracts words included in the event name by performing morphological analysis on each event name described in each piece of schedule information collected by the collection unit 52.

  However, the word extraction unit 53 does not redundantly extract the same word. For example, when the word "artificial intelligence" has already been extracted, the word extraction unit 53 ignores the word "artificial intelligence" extracted after the second time. This point is the same as the word extraction unit 3 described above.

  For example, the word extraction unit 53 extracts words such as “artificial intelligence”, “development”, and “meeting” by executing morphological analysis on an event name “artificial intelligence development conference”.

  The word extraction unit 53 obtains a set of words by performing this process on each event name described in each schedule information. The words belonging to this set are different from one another because identical words are not extracted redundantly.

  The score calculation unit 54 calculates, for each combination of each person belonging to the tissue and each word extracted by the word extraction unit 53, a relation score indicating the strength of the association between the person and the word. This association score is similar to the association score in the first to third embodiments. However, in the fourth embodiment, the key touch number is not used as the association score. That is, the word extraction unit 53 does not calculate the relevance score by the second calculation method described in the first embodiment.

  Hereinafter, two types of methods will be described as the method of calculating the relevance score in the fourth embodiment. In any of the following two types of methods, the score calculation unit 54 calculates the association score for each combination of a person and a word, and causes the storage unit 5 to store the association score.

  The first calculation method of the relevance score in the fourth embodiment is the same method as the first calculation method of the relevance score in the first embodiment. However, instead of the file operation time, the event participation time is used.

  The first method of calculating the relevance score in the fourth embodiment is an event in which the word W is an event as a relevance score for one person (hereinafter referred to as person H) and one word (hereinafter referred to as word W). It is a method of calculating the total of the event participation time of the person H to each event included in the name. As the event participation time is longer, the relation between the person H and the word W is stronger, and as the event participation time is shorter, the relation between the person H and the word W is weaker. Therefore, event participation time can be used as a related score.

  In the first calculation method, the score calculation unit 54 calculates the sum of the event participation time of the person H for each event including the word W in the event name, and sets the sum as the association score between the person H and the word W.

  That is, the score calculation unit 54 includes the word W in the event name, calculates the event participation time for each event in which the person H participates, and sets the total as the association score between the person H and the word W.

  The second calculation method of the relevance score in the fourth embodiment is the same method as the third calculation method of the relevance score in the first embodiment. However, instead of the file operation time, the event participation time is used.

The second calculation method of the association score in the present embodiment is a method of calculating the association score of one person (person H) and one word (word W) based on two ratios described below. Of the two proportions, one proportion is noted Q ₁ and the other proportion is noted Q ₂ .

Q ₁ is the ratio of the sum of event participation time of person H to each event including word W in the event name to the sum of the event participation time of all persons in the organization for each event including word W in the event name . That is, Q ₁ is represented by the following equation (7).

Q ₂ is the event participation time of the person H for each event including the word W in the event name with respect to the total of the event participation time of the person H for each event including the focused word in the event name when focusing on individual words The ratio of the sum of That is, Q2 is represented by the following equation (8).

Q ₁ will be explained. The sum total of the event participation time of the person H for each event including the word W in the event name (the numerator on the right side of the equation (7)) corresponds to the association score calculated by the first calculation method described above. That is, the score calculation unit 54 may calculate the total of the event participation time of the person H with respect to each event including the word W in the event name by the method described in the first calculation method described above.

  The sum (the denominator of the right side of the right side of Formula (7)) of the event participation time of all persons in the organization for each event including the word W in the event name will be described. The score calculation unit 54 also calculates, for each event including the word W in the event name, the sum of the event participation time of the first person in the organization by the method described in the first calculation method described above. Similarly, the score calculation unit 54 calculates, for each event including the word W in the event name, the sum of the event participation time of the second person in the organization by the method described in the first calculation method described above. Similarly, the score calculation unit 54 calculates, for each person belonging to the organization, the sum total of the person's event participation time for each event including the word W in the event name. Furthermore, the score calculation unit 54 calculates the total sum of “sum of person's event participation time for each event including the word W in the event name” calculated for each person belonging to the organization. This value corresponds to the sum of event participation times of all persons in the organization for each event including the word W in the event name.

The score calculation unit 54 calculates Q ₁ by the calculation of Expression (7) using the numerator and denominator of the right side of Expression (7) calculated as described above.

Next, the _{Q 2} will be described. The numerator on the right side of Formula (8) is the same as the numerator on the right side of Formula (7). Therefore, the score calculation unit 54 may calculate the total of the event participation time of the person H for each event including the word W in the event name by the method described in the first calculation method described above.

  The sum (the denominator on the right side of the right side of the equation (8)) of the event participation time of the person H for each event including the focused word in the event name when focusing on each word will be described. The score calculation unit 54 focuses on the individual words extracted by the word extraction unit 53 (in other words, selects individual words one by one). Then, the score calculation unit 54 calculates the total of the event participation time of the person H with respect to each event including the focused word (selected word) in the event name by the method described in the first calculation method described above. The score calculation unit 54 focuses on the next word (in other words, selects the next word), and adds up the sum of the event participation time of the person H for each event that includes the focused word (selected word) in the event name. The calculation is performed by the method described in the first calculation method described above. As described above, the score calculation unit 54 calculates, for each word, the sum of the event participation time of the person H for each event including the word in the event name. Then, the score calculation unit 54 calculates the sum of “the sum of the event participation time of the person H for each event including the word in the event name” calculated for each word. This value corresponds to the denominator of equation (8). The “sum of the event participation time of person H for each event that includes the focused word in the event name (the denominator on the right side of equation (8)) when focusing on the individual word” is “each including the word in the event name It can be said that the total sum of the participation time of the person H for the event is the sum total of the total sum when the total sum is calculated for each word.

The score calculation unit 54 calculates Q ₂ by the calculation of Expression (8) using the numerator and denominator of the right side of Expression (8) calculated as described above.

After obtaining Q ₁ and Q ₂ , the score calculation unit 54 calculates the relation score between the person H and the word W by the following equation (9).

Related score = Q ₁ × log (Q ₂ ) (9)

  When the relevance score is calculated by the second calculation method in the fourth embodiment, the same effect as that when the relevance score is calculated by the third calculation method described in the first embodiment can be obtained.

  The collection unit 52 is realized by, for example, a CPU of a computer that operates according to a related score calculation program and a communication interface of the computer. For example, the CPU may read the related score calculation program from a program storage medium such as a program storage device of a computer, and operate as the collection unit 52 using a communication interface according to the related score calculation program. The word extraction unit 53 and the score calculation unit 54 are also realized by, for example, the CPU of the above-described computer that operates in accordance with the related score calculation program. That is, as described above, the CPU reading the related score calculation program may operate as the word extraction unit 53 and the score calculation unit 54 according to the related score calculation program. The storage unit 5 is realized by the storage device of the computer described above. Also, the collection unit 52, the word extraction unit 53, and the score calculation unit 54 may be realized by separate hardware.

  The fourth embodiment may be applied to a modification of the first embodiment (see FIG. 5), a second embodiment (see FIG. 7), and a third embodiment (see FIG. 14). That is, in the modification of the first embodiment (see FIG. 5), the collecting unit 2, the word extracting unit 3 and the score calculating unit 4 are the same as the collecting unit 52, the word extracting unit 53 and the score described in the fourth embodiment. The calculation unit 54 may be substituted. In the second embodiment (see FIG. 7), the collecting unit 2, the word extracting unit 3 and the score calculating unit 4 are the same as the collecting unit 52, the word extracting unit 53 and the score calculating unit 54 described in the fourth embodiment. May be replaced by In the third embodiment (see FIG. 14), the collecting unit 2, the word extracting unit 3 and the score calculating unit 4 are the same as the collecting unit 52, the word extracting unit 53 and the score calculating unit 54 described in the fourth embodiment. May be replaced by

  FIG. 18 is a schematic block diagram showing a configuration example of a computer according to each embodiment of the present invention. The computer 1000 includes a CPU 1001, a main storage 1002, an auxiliary storage 1003, an interface 1004, and a communication interface 1005.

  The relevance score calculation system 1 of each embodiment of the present invention is implemented in a computer 1000. The operation of the relevance score calculation system 1 is stored in the auxiliary storage device 1003 in the form of a relevance score calculation program. The CPU 1001 reads out the related score calculation program from the auxiliary storage device 1003 and expands it in the main storage device 1002, and executes the above processing according to the related score calculation program.

  The auxiliary storage device 1003 is an example of a non-temporary tangible medium. Other examples of non-transitory tangible media include a magnetic disk connected via an interface 1004, a magneto-optical disk, a compact disk read only memory (CD-ROM), a digital versatile disk read only memory (DVD-ROM), Semiconductor memory etc. are mentioned. When this program is distributed to the computer 1000 by a communication line, the computer 1000 that has received the distribution may deploy the program in the main storage device 1002 and execute the above processing.

  Also, the program may be for realizing a part of the above-mentioned processing. Furthermore, the program may be a difference program that realizes the above-described processing in combination with other programs already stored in the auxiliary storage device 1003.

  In addition, part or all of each component may be realized by a general purpose or special purpose circuit (circuitry), a processor or the like, or a combination thereof. These may be configured by a single chip or may be configured by a plurality of chips connected via a bus. Some or all of the components may be realized by a combination of the above-described circuits and the like and a program.

  When a part or all of each component is realized by a plurality of information processing devices, circuits, and the like, the plurality of information processing devices, circuits, and the like may be centrally disposed or may be distributed. For example, the information processing apparatus, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client and server system, a cloud computing system, and the like.

  Next, an outline of the present invention will be described. FIG. 19 is a block diagram showing an outline of the present invention. The relevance score calculation system of the present invention includes a collection unit 82, a word extraction unit 83, and a relevance score calculation unit 84.

  The collection unit 82 (for example, the collection unit 2) collects, from the terminal device, an operation log that is a record of the user operating the file.

  The word extraction unit 83 (for example, the word extraction unit 3) extracts a word from the file name described in each operation log.

  The association score calculation unit 84 (for example, the score calculation unit 4) calculates an association score representing the degree of association between the user and the word based on each operation log.

  Such a configuration can clarify the strength of the association between people and words in the organization.

  FIG. 20 is a block diagram showing another example of the outline of the present invention. The relevance score calculation system of the present invention includes a collection unit 86, a word extraction unit 87, and a relevance score calculation unit 88.

  The collection unit 86 (for example, the collection unit 52) collects schedule information that describes a person, an event name, and a time zone in which the person is involved in the event having that event name.

  The word extraction unit 87 (for example, the word extraction unit 53) extracts a word from the event name described in each piece of schedule information.

  The association score calculation unit 88 (for example, the score calculation unit 54) calculates an association score representing the degree of association between a person and a word based on each piece of schedule information.

  Such configuration also makes it possible to clarify the strength of association between people in the organization and words.

  Although each embodiment of the above-mentioned present invention may be described as the following supplementary notes, it is not necessarily limited to the following.

(Supplementary Note 1)
A collection unit that collects, from the terminal device, an operation log that is a record when the user operates the file;
A word extraction unit for extracting words from file names described in each operation log;
A related score calculation system, comprising: a related score calculation unit that calculates a related score representing the strength of a relation between a user and a word based on each operation log.

(Supplementary Note 2)
The association score calculation unit calculates, as the association score of one user and one word, the sum of the operation time of the one user for each file including the one word in the file name. Calculation system.

(Supplementary Note 3)
The association score calculation unit calculates, as the association score of one user and one word, a sum of the number of key touches when the one user operates each file including the one word in the file name. Related score calculation system described in.

(Supplementary Note 4)
The related score calculation unit
The related score of one user and one word,
The ratio of the sum of the operation time of the one user for each file including the word in the file name to the total operation time of all users in the organization for each file including the one word in the file name ,
When the sum of the operation time of the one user for each file including the word in the file name is determined for each word, the one user for each file including the one word in the file name with respect to the total sum of the sum The related score calculation system according to Appendix 1, which is calculated based on the ratio of the total operation time of.

(Supplementary Note 5)
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept words as search keywords,
The search unit is
The association score calculation system according to any one of appendixes 1 to 4, wherein a user ID corresponding to the word is searched based on the association score.

(Supplementary Note 6)
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept user ID as search keyword,
The search unit is
The association score calculation system according to any one of Appendixes 1 to 5, wherein a word corresponding to the user ID is searched based on the association score.

(Appendix 7)
A first table generation unit that generates a first table describing a relationship among a user ID, a word, and a related score;
A second table generation unit that generates a second table describing a degree of association representing the degree of association between the words calculated based on the first table;
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept words as search keywords,
The search unit is
The association score calculation system according to any one of appendixes 1 to 4, wherein a user ID corresponding to the word is searched based on the first table and the second table.

(Supplementary Note 8)
A first table generation unit that generates a first table describing a relationship among a user ID, a word, and a related score;
A second table generation unit that generates a second table describing a degree of association representing the degree of association between the words calculated based on the first table;
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept user ID as search keyword,
The search unit is
The related score calculation system according to any one of supplementary notes 1 to 4 and supplementary note 7, wherein a word corresponding to the user ID is searched based on the first table and the second table.

(Appendix 9)
A clustering unit that clusters words based on the second table;
A word presentation unit that presents a word for each cluster;
A deletion target reception unit that receives designation of a word to be excluded from the first table and the second table among the presented words;
The first table generator is
Regenerate the first table, excluding the words specified as the words to be excluded,
The second table generator is
The related score calculation system according to Appendix 7 or 8, wherein a second table is generated again based on the first table.

(Supplementary Note 10)
A collection unit for collecting schedule information describing a person, an event name, and a time zone in which the person has been involved in the event having the event name;
A word extraction unit for extracting a word from an event name described in each schedule information;
A related score calculation system, comprising: a related score calculation unit that calculates a related score representing the strength of a relation between a person and a word based on each piece of schedule information.

(Supplementary Note 11)
Collecting from the terminal device an operation log that is a record of the user operating the file;
Extract words from the file name described in each operation log,
A related score calculation method, comprising: calculating, based on each operation log, a related score representing the strength of the relation between a user and a word.

(Supplementary Note 12)
Collecting schedule information describing a person, an event name, and a time zone in which the person was involved in the event having the event name;
Extract words from the event name described in each schedule information,
A relation score calculation method, comprising: calculating a relation score representing the strength of a relation between a person and a word based on each piece of schedule information.

(Supplementary Note 13)
On the computer
Collection processing for collecting, from the terminal device, an operation log that is a record of a user operating a file;
Word extraction processing for extracting a word from a file name described in each operation log;
A related score calculation program for executing a related score calculation process for calculating a related score representing the strength of the relation between a user and a word based on each operation log.

(Supplementary Note 14)
On the computer
A collection process for collecting schedule information describing a person, an event name, and a time zone in which the person is involved in an event having the event name;
Word extraction processing for extracting words from event names described in each schedule information, and
A related score calculation program for executing a related score calculation process for calculating a related score representing the strength of a relation between a person and a word based on each schedule information.

  The present invention is suitably applied to a relation score calculation system that quantifies the strength of a relation between a person and a word.

Reference Signs List 1 related score calculation system 2, 52 collection unit 3, 53 word extraction unit 4, 54 score calculation unit 5 storage unit 6 keyword reception unit 7, 17 search unit 8 output unit 31 clustering unit 32 cluster output unit 33 exclusion target word reception unit

Claims (14)

A collection unit that collects, from the terminal device, an operation log that is a record when the user operates the file;
A word extraction unit for extracting words from file names described in each operation log;
A related score calculation system, comprising: a related score calculation unit that calculates a related score representing the strength of a relation between a user and a word based on each operation log. The association score calculation unit calculates, as the association score of one user and one word, the sum of the operation time of the one user for each file including the one word in the file name. Score calculation system. The association score calculation unit calculates, as the association score of one user and one word, a sum of the number of key touches when the one user operates each file including the one word in the file name. The related score calculation system described in 1. The related score calculation unit
The related score of one user and one word,
The ratio of the sum of the operation time of the one user for each file including the word in the file name to the total operation time of all users in the organization for each file including the one word in the file name ,
When the sum of the operation time of the one user for each file including the word in the file name is determined for each word, the one user for each file including the one word in the file name with respect to the total sum of the sum The related score calculation system according to claim 1, which is calculated based on the ratio of the total operation time of. A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept words as search keywords,
The search unit is
The related score calculation system according to any one of claims 1 to 4, wherein a user ID corresponding to the word is searched based on the related score. A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept user ID as search keyword,
The search unit is
The related score calculation system according to any one of claims 1 to 5, wherein a word corresponding to the user ID is searched based on the related score. A first table generation unit that generates a first table describing a relationship among a user ID, a word, and a related score;
A second table generation unit that generates a second table describing a degree of association representing the degree of association between the words calculated based on the first table;
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept words as search keywords,
The search unit is
The relation score calculation system according to any one of claims 1 to 4, wherein a user ID corresponding to the word is searched based on the first table and the second table. A first table generation unit that generates a first table describing a relationship among a user ID, a word, and a related score;
A second table generation unit that generates a second table describing a degree of association representing the degree of association between the words calculated based on the first table;
A keyword receiving unit for receiving search keywords;
And a search unit that executes a search according to a search keyword,
The keyword accepting unit is
Accept user ID as search keyword,
The search unit is
The related score calculation system according to any one of claims 1 to 4 and claim 7, wherein a word corresponding to the user ID is searched based on the first table and the second table. . A clustering unit that clusters words based on the second table;
A word presentation unit that presents a word for each cluster;
A deletion target reception unit that receives designation of a word to be excluded from the first table and the second table among the presented words;
The first table generator is
Regenerate the first table, excluding the words specified as the words to be excluded,
The second table generator is
The related score calculation system according to claim 7, wherein a second table is generated again based on the first table. A collection unit for collecting schedule information describing a person, an event name, and a time zone in which the person has been involved in the event having the event name;
A word extraction unit for extracting a word from an event name described in each schedule information;
A related score calculation system, comprising: a related score calculation unit that calculates a related score representing the strength of a relation between a person and a word based on each piece of schedule information. Collecting from the terminal device an operation log that is a record of the user operating the file;
Extract words from the file name described in each operation log,
A related score calculation method, comprising: calculating, based on each operation log, a related score representing the strength of the relation between a user and a word. Collecting schedule information describing a person, an event name, and a time zone in which the person was involved in the event having the event name;
Extract words from the event name described in each schedule information,
A relation score calculation method, comprising: calculating a relation score representing the strength of a relation between a person and a word based on each piece of schedule information. On the computer
Collection processing for collecting, from the terminal device, an operation log that is a record of a user operating a file;
Word extraction processing for extracting a word from a file name described in each operation log;
A related score calculation program for executing a related score calculation process for calculating a related score representing the strength of the relation between a user and a word based on each operation log. On the computer
A collection process for collecting schedule information describing a person, an event name, and a time zone in which the person is involved in an event having the event name;
Word extraction processing for extracting words from event names described in each schedule information, and
A related score calculation program for executing a related score calculation process for calculating a related score representing the strength of a relation between a person and a word based on each schedule information.

Images