Solution proposal method, classification model generation method, and solution proposal system

Abstract

To provide a proposal method of solution means and proposal system for detecting a proper past subject similar to a novel subject, and a generation method of a classification model used for the proposal method of the solution means.SOLUTION: A proposal method of solution means is configured so that: using a classification model learned in teacher data in which, subject tags c4 each of which corresponds to each of multiple past subjects a11, are classified into multiple categories D4 according to mutual relevance, a category to which the new subject is classified, is estimated; in the estimated category, a past subject similar to the new subject is searched; then, solution means associated with the searched and similar past subject, is output. Each past subject is input to any subject item, in at least one hierarchical data. Each subject tag is determined on the basis of the information input to an item which has a parental relation with the subject item to which each past subject is input, in each past subject and hierarchical data.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The embodiments relate to a solution suggestion method, a classification model generation method, and a solution suggestion system. [Background technology]

[0002] Conventionally, a set of data has been accumulated that links past problems to solutions, and when considering solutions to a new problem, attempts have been made to search the accumulated set of data for past problems that are similar to the new problem and to utilize the solutions of similar past problems. However, in some cases, the characteristics of past assignments are not fully expressed, making it impossible to find appropriate past assignments similar to the new assignment from the accumulated set data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2000-276487 Summary of the Invention [Problem to be solved by the invention]

[0004] The purpose of the embodiment is to provide a solution suggestion method and system that can detect appropriate past problems that are similar to a new problem, and a method for generating a classification model to be used in such a solution suggestion method. [Means for solving the problem]

[0005] A method for proposing a solution means according to an embodiment includes the steps of: acquiring a new assignment; using a classification model trained with teacher data in which assignment tags corresponding to each of a plurality of past assignments are classified into a plurality of categories according to their mutual relevance, estimating which of the plurality of categories the new assignment will be classified into; searching for a past assignment among the plurality of past assignments within the estimated category that is similar to the new assignment; and outputting a solution means linked to the searched similar past assignment; each of the past assignments is entered into one of the assignment items within at least one hierarchical data in which assignment items and means items are arranged in a hierarchical structure, and each of the assignment tags is determined based on information entered into each of the past assignments and into items in the hierarchical data that have a parent-child relationship with the assignment item into which each of the past assignments is entered. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a block diagram showing a system for proposing a solution according to a first embodiment and a system for generating a classification model used in the system. [Figure 2] FIG. 10 is a diagram illustrating an example of hierarchical data. [Figure 3] 4 is a flowchart showing a method for generating a classification model according to the first embodiment. [Figure 4] FIG. 1 illustrates a method for determining issue tags. [Figure 5] FIG. 1 illustrates a method for determining issue tags. [Figure 6] FIG. 10 illustrates a method for classifying multiple assignment tags into multiple categories. [Figure 7] 1 is a flowchart showing a method for proposing a solution according to the first embodiment. [Figure 8] FIG. 1 illustrates a method for estimating the category into which a new task falls. [Figure 9] 10 is a graph showing the maximum value of the relevance degree for each category. [Figure 10] FIG. 10 is a diagram showing a method for searching for similar past assignments. [Figure 11] FIG. 10 is a diagram illustrating an example of an output. [Figure 12] Figure 12(a) is a diagram showing a method for estimating a category into which a new assignment will be classified in a system for proposing a solution according to the second embodiment, and Figure 12(b) is a diagram showing a method for extracting a past assignment that is similar to a new assignment from among multiple past assignments in a system for proposing a solution according to the second embodiment. [Figure 13] FIG. 10 is a diagram showing a search condition setting screen of the solution proposing system according to the second embodiment. [Figure 14] FIG. 10 is a diagram showing an output of the solution proposing system according to the second embodiment. [Figure 15] FIG. 11 is a diagram showing a method for determining a problem tag in the solution proposal system according to the third embodiment. [Figure 16] FIG. 13 is a diagram showing past data according to the fourth embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] First Embodiment First, the first embodiment will be described. (Outline of the solution proposal system) FIG. 1 is a block diagram showing a system for proposing a solution according to this embodiment and a system for generating a classification model used in the system. A proposed system 1 (hereinafter simply referred to as "proposed system 1") of a solution according to this embodiment is used, for example, in an organization consisting of multiple domains. A "domain" is a business area in which an organization such as a company develops its business.

[0008] When a new problem i1 is input from a terminal in one of the domains, the proposed system 1 searches for a past problem a11 similar to the new problem i1 from multiple past problems accumulated within the organization, and outputs a solution a12 for the similar past problem a11. This allows past knowledge to be utilized regardless of the domain when considering a solution for the new problem i1 in each domain. Note that the proposed system 1 may be used within a single domain.

[0009] The proposed system 1 is based on the premise that at least one hierarchical data D1 (past data) is provided from each domain, a classification model D5 generated by a generation system 2 using the hierarchical data D1, and set data D2. Before describing the configuration of the proposed system 1 in detail, the hierarchical data D1 and the generation system 2 will first be described in detail.

[0010] (hierarchical data) FIG. 2 is a diagram illustrating hierarchical data. The hierarchical data D1 is data that breaks down the knowledge that was considered in the past when realizing an object such as technology or a product into problems that arose when realizing the object and the means that can solve those problems, and links the means to the problems. By creating the hierarchical data D1, it is possible to organize the knowledge that was considered in the past when realizing the object.

[0011] In the hierarchical data D1, task item a1 and means item a2 are arranged in a hierarchical structure. A "hierarchical structure" refers to a structure having multiple levels arranged from top to bottom, where an item Y, which is a prerequisite for a certain item X, is arranged in the level immediately below the level where the item X is arranged, and the lower-level item Y is linked to the higher-level item X. Hereinafter, this relationship between item X and item Y is referred to as a "parent-child relationship." Furthermore, from the perspective of item Y, item X is referred to as a "parent item," and item Y is referred to as a "child item." Furthermore, if item Z is arranged in the level immediately below the level where item Y is arranged and linked to item Y, item Z is referred to as a "grandchild item" from the perspective of item X. The hierarchical data D1 may also be configured as a hierarchical structure that includes additional items in addition to task item a1 and means item a2. In such a case, multiple items, including task item a1 and means item a2, are arranged in the hierarchical data D1 to form a hierarchical structure.

[0012] In the example of Figure 2, target item a0 is placed at the top (root) of hierarchical data D1. For example, target technology, products, etc. are input into target item a0. A child item of target item a0 is problem item a1 that arises when realizing target item a0. A child item of problem item a1 is means item a2 that can solve problem item a1, or another problem item a1 that is obtained by subdividing problem item a1 into multiple subconcepts. A child item of means item a2 is problem item a1 that arises when means item a2 is adopted, or another means item a2 that is obtained by subdividing means item a2 into multiple subconcepts. In the hierarchical data D1, when a plurality of child items are linked to one parent item, the child items are of the same type.

[0013] The proposal system 1 and the generation system 2 treat an assignment that is input to any assignment item a1 in at least one piece of hierarchical data D1 as a "past assignment a11." Furthermore, the proposal system 1 and the generation system 2 treat, for example, the means that were actually adopted to solve the past problem a11 among the means entered in the means item a2 of the descendants such as children and grandchildren of the problem item a1 in which the past problem a11 was entered as the "solution means a12." Note that the proposal system 1 and the generation system 2 may also treat, for example, all the means, including the means that were not adopted, among the means entered in the means item a2 of the descendants of the problem item a1 in which the past problem a11 was entered as the "solution means a12."

[0014] (Configuration of a classification model generation system) Next, the configuration of the generation system 2 will be described. As shown in FIG. 1, the generation system 2 includes a tag determination unit 21, a data creation unit 22, and a model generation unit .

[0015] The tag determination unit 21 determines the assignment tag c4 corresponding to each past assignment a11 based on the information entered for each past assignment a11 and for the items in the hierarchical data D1 that have a parent-child relationship with the assignment item a1 into which the past assignment a11 was entered. The "items in a parent-child relationship" are the parent item b1 and child item b2 of the assignment item a1 into which the past assignment a11 was entered, as shown in Figure 2.

[0016] The assignment tag c4 is determined based on, for example, words extracted from the sentences of each past assignment a11 and the sentences entered in the parent item b1 and child item b2, and synonyms of the extracted words. As shown in Figure 1, the tag determination unit 21 uses, for example, an ontology D3 to search for synonyms and determine the assignment tag c4.

[0017] Ontology D3 systematizes the relationships between concepts used in multiple domains. Even if a problem has the same meaning, it may be expressed using different words in different domains. Ontology D3 is a concept dictionary that incorporates, for example, the relationships between words used in each domain, and systematizes the hierarchical relationships and synonymous relationships between words.

[0018] The data creation unit 22 creates training data D4 in which multiple task tags c4 are classified into multiple categories according to their mutual relevance. Specifically, the data creation unit 22 uses the ontology D3 to divide the multiple task tags c4 into task tag groups that can be grouped under a unified concept across domains. The data creation unit 22 treats one task tag group as one category. In other words, each category contains multiple task tags c4 that can be grouped under a unified concept across domains. Therefore, a "domain" is the business area of ​​an organization, such as "train air conditioning business" or "nuclear power business," while a "category" is a task performed in common across multiple domains, such as "procurement" or "installation."

[0019] The data creation unit 22 also creates set data D2, which is organized by category, by linking the past issues a11 and solutions a12 extracted from the hierarchical data D1 to the issue tag c4. The set data D2 is provided to the search unit 13 and output unit 14 of the proposal system 1, which will be described later.

[0020] The model generation unit 23 generates a classification model D5 using the training data D4 created by the data creation unit 22. The generated classification model D5 is provided to the estimation unit 12 of the proposal system 1, which will be described later, and is used by the estimation unit 12 to estimate the category into which the new task i1 is classified.

[0021] The classification model D5 is a text classification model. For example, the classification model D5 is a multi-class classification model that allows one new task i1 to be classified into multiple categories. A technique used in the classification model D5 is, for example, a neural network. An example of a text classification model using a neural network is fastText, an open source software from Facebook, Inc.

[0022] However, the method used for the classification model D5 is not limited to the above and may be, for example, a support vector machine (SVM), a k-nearest neighbor method, logistic regression, etc. Furthermore, the classification model may be an exclusive classification model that classifies one new task i1 into only one category.

[0023] The classification model D5 created in this way can, for example, take an arbitrary word as input and output the degree of association of the input word in each category.

[0024] (Configuration of the proposed solution system) Next, the configuration of the proposed system 1 will be described. The proposed system 1 includes an input unit 11, an estimation unit 12, a search unit 13, and an output unit 14.

[0025] The input unit 11 accepts input to the proposal system 1. Users in each domain use their terminals to input new assignments i1, set search conditions, and issue search instructions to the proposal system 1. The input unit 11 receives search instructions from the terminals and acquires the new assignments i1, search conditions, etc.

[0026] The estimation unit 12 uses the classification model D5 provided by the generation system 2 to estimate the category into which the new task i1 is classified from among a plurality of categories.

[0027] The search unit 13 refers to the set data D2 in which multiple past assignments a11 are organized by category, and searches for past assignments a11 similar to the new assignment i1 among the multiple past assignments a11 within the estimated category. In this way, past assignments a11 similar to the new assignment i1 are searched for within a category to which highly related past assignments a11 belong. Therefore, it is possible to detect an appropriate past assignment a11 similar to the new assignment i1.

[0028] When searching for a previous assignment a11 similar to the new assignment i1, the search unit 13 may use a vectorization tool D6 that vectorizes text. Examples of the vectorization tool D6 include Word2Vec and Doc2Vec. The vectorization tool D6 has been trained using, for example, text entered in each item in the hierarchical data D1 as training data.

[0029] The search unit 13 uses the vectorization tool D6 to vectorize the text of the new assignment i1 and the text of each past assignment a11 belonging to the estimated category. For example, for each category, the search unit 13 determines that the past assignment a11 represented by a vector that is closest to the vector representing the new assignment i1 is the past assignment a11 similar to the new assignment i1. Note that the search unit 13 may detect past assignments a11 represented by vectors whose distance from the vector representing the new assignment i1 is equal to or less than a threshold, and determine the detected past assignments a11 as the past assignment a11 similar to the new assignment i1.

[0030] The output unit 14 refers to the set data D2 provided by the generation system 2 and outputs a solution a12 for a past assignment a11 that is similar to the new assignment i1.

[0031] The proposal system 1 and the generation system 2 are realized, for example, by a server having a CPU (Central Processing Unit) and memory and connected to terminals in the respective domains. The server may be configured by one computer or multiple computers. The proposal system 1 and the generation system 2 may be realized by separate computers. Furthermore, the hardware that realizes the proposal system and the generation system is not limited to a server. For example, the proposal system and the generation system may be realized by a computer that performs processing using various data, such as new tasks and past data, uploaded to the cloud. Furthermore, the hardware that realizes the proposal system and the hardware that realizes the generation system may be different.

[0032] (How to generate a classification model) FIG. 3 is a flowchart showing a method for generating a classification model according to this embodiment. 4 and 5 are diagrams illustrating a method for determining an issue tag. Next, a method for generating a classification model according to this embodiment will be described using a specific example. First, as shown in Figures 3 to 5, the tag determination unit 21 of the generation system 2 determines an assignment tag c4 corresponding to each past assignment a11 based on the information entered into each past assignment a11 and into items b1 and b2 that have a parent-child relationship with the assignment item a1 into which each past assignment a11 was entered within the hierarchical data D1 (step S11).

[0033] More specifically, as shown in FIG. 4, the tag determination unit 21 performs morphological analysis on the sentence in the past assignment a11, the sentence entered in the parent item b1, and the sentence entered in the child item b2, and extracts words (independent words) from each sentence, excluding particles and auxiliary verbs (step S11a). Hereinafter, the extracted words will be referred to as "extracted words c1." That is, using the example of FIG. 4, the sentence in the past assignment a11 is "product durability." The sentence entered in the parent item b1 is "procurement work for semiconductor application products." The sentences entered in the five child items b2 are "appropriate design," "appropriate material selection," "appropriate manufacturing," "appropriate inspection," and "appropriate shipping and transportation." The independent words in these sentences are extracted words c1.

[0034] Next, the tag determination unit 21 refers to the ontology D3 and adds synonyms c2 for each extracted term c1 (step S11b).

[0035] Next, as shown in FIG. 5, the tag determination unit 21 determines a representative word c3 of the extracted words c1 and the synonyms c2 using the ontology D3 (step S11c). Specifically, first, the tag determination unit 21 divides the extracted words c1 and the synonyms c2 into word groups g that can be grouped under a unified concept using the ontology D3. Next, the tag determination unit 21 selects several word groups g from the word groups g. The selection method is not particularly limited, but for example, word groups g with low priority from the viewpoint of expressing the problem or the like may be removed, and then the top word groups g containing the largest number of words may be selected.

[0036] Next, the tag determination unit 21 determines a representative word c3 that aggregates the extracted words c1 and synonyms c2 contained in each selected word group g. Each representative word c3 may be, for example, a hypernym of the extracted words c1 and synonyms c2 contained in each word group g, or may be any of the extracted words c1 and synonyms c2 contained in each word group g. In the example of Fig. 5, the number of representative words c3 is six, but the number of representative words c3 is not particularly limited.

[0037] Next, the tag determination unit 21 determines a task tag c4 based on the determined representative words c3 (step S11d). The task tag c4 may be a combination of all the representative words c3, or may be a word or combination of words that aggregates the determined representative words c3. In the figure, for convenience, each task tag c4 is represented by a string of characters that combines "Y" with a number.

[0038] The tag determination unit 21 determines the assignment tag c4 based on the information entered not only in the past assignment a11 but also in the parent-child items b1 and b2. For this reason, using Figures 4 and 5 as an example, the assignment tag c4 includes features such as "procurement," "design," "manufacturing," and "transportation" that are not expressed in the sentence "product durability" in the past assignment a11. In this way, the assignment tag c4 includes features of information from higher and lower hierarchical levels of the past assignment a11.

[0039] The tag determination unit 21 also determines assignment tags c4 based on extracted words c1 and synonyms c2 of extracted words c1 extracted from the sentences of each past assignment a11 and the sentences entered in the parent-child items b1 and b2. This allows an appropriate assignment tag c4 to be assigned to each past assignment a11, without being limited to the expressions in the sentences of the past assignment a11 and the sentences entered in the parent-child items b1 and b2.

[0040] The method for determining the task tag c4 is not limited to the above. For example, the task tag c4 may be determined manually by an expert or by a combination of a mechanical method and a manual method, rather than being determined mechanically by the tag determination unit 21 using the ontology D3 or the like.

[0041] FIG. 6 is a diagram showing a method for classifying multiple issue tags into multiple categories. As shown in FIG. 6, in the above-described step S11, an assignment tag c4 is assigned to each past assignment a11 in each domain.

[0042] Next, the data creating unit 22 creates training data D4 in which a plurality of task tags c4 are classified into a plurality of categories according to their mutual relevance (step S12). In step S12, for example, the data creation unit 22 uses the ontology D3 to divide multiple task tags c4 into task tag groups h that can be grouped under a unified concept across multiple domains. The data creation unit 22 treats one task tag group h as one category. Note that in this case, for example, one task tag c4 may belong to multiple categories. In the example shown in Figure 6, the categories include "procurement," "installation," "product," "maintenance," "design," "production," and "transportation."

[0043] The method for creating the training data D4 is not limited to the above. For example, the task tags c4 may be manually categorized by an expert or a combination of mechanical and manual methods, rather than being mechanically categorized by the data creating unit 22 using the ontology D3 or the like.

[0044] The data creating unit 22 also creates set data D2 (see FIG. 10) in which the assignment tag c4 is linked to the past assignment a11 and the solution method a12 and organized by category. The data creating unit 22 provides the set data D2 to the search unit 13.

[0045] Next, the model generation unit 23 generates a classification model D5 using the training data D4 (step S13). The classification model D5 generated by the model generation unit 23 is provided to the estimation unit 12 of the proposal system 1.

[0046] When generating a classification model D5 using the training data D4, all of the training data D4 created by the data creation unit 22 may be used to train the classification model D5, or only a portion of the training data D4 created by the data creation unit 22 may be used to train the classification model D5.

[0047] (How to propose a solution) FIG. 7 is a flowchart showing a method for proposing a solution according to this embodiment. Next, a method for proposing a solution according to this embodiment will be described. First, a user uses a terminal to input a new assignment i1, set search conditions, and issue a command to start a search to the proposal system 1. The input unit 11 receives the command to start a search and acquires the new assignment i1, the search conditions, etc. (step S21).

[0048] Next, the estimation unit 12 estimates the category into which the new task i1 is classified from among the multiple categories using the classification model D5 that has been trained in step S13 (step S22).

[0049] FIG. 8 is a diagram illustrating a method for estimating a category into which a new task will be classified. For example, the estimation unit 12 extracts a plurality of partial words i2 by shifting their positions from the sentence of the new task i1. For example, the estimation unit 12 sequentially extracts partial words i2 each consisting of three characters while shifting the extraction start position by one character at a time. However, the number of characters in the partial word i2 and the number of characters to be shifted are not limited to those described above.

[0050] Next, the estimation unit 12 inputs the extracted multiple partial words i2 to the classification model D5, and causes the classification model D5 to output the relevance i3 between each partial word i2 and each category. For example, the classification model D5 calculates, for each partial word i2, a vertical vector V whose components are the relevance i3 with each category. Hereinafter, the horizontal arrangement of the vertical vectors V for each partial word i2 is referred to as the relevance matrix M.

[0051] Next, the estimation unit 12 calculates the maximum value of the relevance i3 of each category in the relevance matrix M, and determines whether the maximum value calculated for each category is equal to or greater than a threshold. In the example of FIG. 8, the maximum value of the relevance i3 of the "procurement" category is 0.77. The maximum value of the relevance i3 of the "installation" category is 0.99. The maximum value of the relevance i3 of the "product" category is 0.11. The maximum value of the relevance i3 of the "maintenance" category is 0.73.

[0052] FIG. 9 is a graph showing the maximum relevance values ​​for each category. As shown in Fig. 9, the estimation unit 12 estimates that the category in which the new task i1 is classified is the category in which the maximum value of the relevance degree i3 is equal to or greater than the threshold. In the example of Fig. 9, the maximum values ​​of the relevance degrees i3 of "installation," "maintenance," and "procurement" exceed the threshold. Therefore, the estimation unit 12 estimates that "installation," "maintenance," and "procurement" are the categories in which the new task i1 is classified. Note that the threshold may be set to an arbitrary value by the user in step S21, for example.

[0053] In this way, multiple partial words i2 are extracted from the sentence of the new task i1 at shifted positions. The classification model D5 then inputs the extracted multiple partial words i2 and outputs the relevance i3 between each partial word i2 and each category. The category into which the new task i1 will be classified is then estimated based on the relevance i3. At least one partial word i2 contains part of a group of words located nearby in the sentence. As a result, it is possible to estimate a contextually related category for the sentence of the new task i1. Note that the method for estimating the category into which the new task i1 will be classified is not limited to the above.

[0054] FIG. 10 is a diagram showing a method for searching for similar past assignments. Next, as shown in FIG. 10, the search unit 13 refers to the set data D2 and searches for past assignments a11 similar to the new assignment i1 from among the multiple past assignments a11 in each of the estimated categories (step S23).

[0055] In step S23, the search unit 13 vectorizes the sentences of the new assignment i1 and the sentences of the past assignments a11 in each estimated category, for example, using the vectorization tool D6.

[0056] Next, the search unit 13 detects, for example, within each category, a past assignment a11 represented by a vector that is closest to the vector representing the new assignment i1, and determines that the detected past assignment a11 is a past assignment a11 that is similar to the new assignment i1.

[0057] In the example shown in FIG. 10, a past assignment a11 with an assignment tag c4 of "Y22" in the "Installation" category is detected as a past assignment a11 similar to the new assignment i1. A past assignment a11 with an assignment tag c4 of "Y21" in the "Maintenance" category is detected as a past assignment a11 similar to the new assignment i1. A past assignment a11 with an assignment tag c4 of "Y33" in the "Procurement" category is detected as a past assignment a11 similar to the new assignment i1. For example, the search unit 13 may search for a past assignment a11 similar to the new assignment i1 among multiple past assignments a11 in a category based on the assignment tag c4. In this case, too, the vectorization tool D6 may be used to vectorize the assignment tag c4 corresponding to the new assignment i1 and the assignment tag c4 corresponding to the estimated past assignments a11 in each category.

[0058] In this way, past assignments a11 similar to the new assignment i1 are searched for within a category to which highly related past assignments a11 belong. This makes it possible to detect appropriate past assignments a11 similar to the new assignment i1. As mentioned above, the assignment tag c4 contains characteristics of information from higher and lower hierarchical levels of the past assignment a11. Therefore, each past assignment a11 is classified into an appropriate category using the assignment tag c4. The method of searching for past assignments a11 similar to the new assignment i1 is not limited to the above.

[0059] FIG. 11 is a diagram illustrating an example of the output. Next, the output unit 14 refers to the set data D2 and outputs the solutions a12 of the similar past assignments a11 for each estimated category (step S24). The output unit 14 outputs, for example, the estimated categories, similar past assignments a11 in each category, and their solutions a12. There may be one or more similar past assignments a11 per category. The user can consider solutions to the new assignment i1 by referring to the output solutions a12.

[0060] The classification model D5 only needs to be generated at least once before the first use of the proposal system 1. For example, the classification model D5 may be generated only once, and the proposal system 1 may use the same classification model D5 each time it estimates the category into which a new task i1 is classified. Furthermore, the classification model D5 may be regenerated, for example, when new hierarchical data D1 is provided or when the contents of existing hierarchical data D1 are updated.

[0061] Next, the effects of this embodiment will be described. In this embodiment, a past assignment a11 similar to the new assignment i1 is searched for within the category into which the new assignment i1 is estimated to be classified. Therefore, a past assignment a11 similar to the new assignment i1 is searched for within a category to which highly related past assignments a11 belong. As a result, an appropriate past assignment a11 similar to the new assignment i1 can be detected.

[0062] Furthermore, in this embodiment, each past assignment a11 is entered into one of the assignment items a1 in at least one hierarchical data D1, in which assignment items a1 and means items a2 are arranged in a hierarchical structure. The assignment tag c4 is determined based on the information entered into each past assignment a11 and into items b1 and b2 that have a parent-child relationship with the assignment item a1 to which the past assignment a11 is entered in the hierarchical data D1. Therefore, the assignment tag c4 contains characteristics of the information in the higher and lower hierarchical levels of the past assignment a11. Therefore, each past assignment a11 can be classified into an appropriate category using the assignment tag c4.

[0063] In this embodiment, each assignment tag c4 is determined based on extracted words c1 and synonyms c2 of extracted words c1 extracted from the sentences of each past assignment a11 and the sentences entered in the parent-child items b1 and b2. This allows an appropriate assignment tag c4 to be assigned to each past assignment a11, without being limited to the expressions in the sentences of the past assignment a11.

[0064] In this embodiment, multiple partial words i2 are extracted from the sentence of the new task i1 at shifted positions. The classification model D5 then receives the extracted multiple partial words i2 as input and outputs the relevance i3 between each partial word i2 and each category. Based on the output relevance i3, the category into which the new task i1 will be classified is estimated from among the multiple categories. At least one partial word i2 includes part of a group of words located in a nearby position in the sentence of the new task i1. As a result, it is possible to estimate contextually related categories for the sentence of the new task i1.

[0065] In this embodiment, each category includes multiple assignment tags c4 that can be grouped under a unified concept across multiple domains. As a result, it is possible to search for an appropriate past assignment a11 that is similar to the new assignment i1, regardless of the domain.

[0066] According to the embodiment described above, it is possible to realize a method and system for proposing a solving means a12 that can detect an appropriate past task a11 that is similar to a new task i1, and a method for generating a classification model D5 that is used in the method for proposing such a solving means a12.

[0067] <Second embodiment> Next, a second embodiment will be described. Figure 12(a) is a diagram showing a method for estimating the category into which a new assignment will be classified in the system for proposing a solution according to this embodiment, and Figure 12(b) is a diagram showing a method for extracting past assignments similar to a new assignment from among multiple past assignments in the system for proposing a solution according to this embodiment. FIG. 13 is a diagram showing a search condition setting screen of the solution proposing system according to this embodiment. FIG. 14 is a diagram showing the output of the solution proposal system according to this embodiment. In the following explanation, in principle, only the differences from the first embodiment will be explained, and matters other than those explained below are the same as those in the first embodiment.

[0068] 12(a), the estimation unit 12 can calculate the degree of association between the new assignment i1 and multiple categories, as in the first embodiment. Then, the estimation unit 12 estimates a category among the multiple categories whose degree of association is equal to or greater than a first threshold TH1 as the category to which the new assignment i1 is classified.

[0069] 12(b), the search unit 13 can calculate the similarity between the new assignment i1 and a similar past assignment a11. Then, the search unit 13 extracts, as similar past assignments a11, past assignments a11 that are classified into the estimated category from among the multiple past assignments a11 and whose similarity to the new assignment i1 is equal to or greater than a second threshold TH2. The similarity is not particularly limited as long as it represents the degree of similarity between the new assignment i1 and the past assignment a11, and examples include cosine similarity or the distance between the new assignment i1 and the past assignment a11 in semantic space.

[0070] As shown in Fig. 13, when a new assignment i1 is input, the input unit 11 also accepts settings of a first threshold TH1 and a second threshold TH2 by the user. For example, before a search, a screen such as that shown in Fig. 13 is displayed on a computer operated by the user. The user inputs the new assignment i1 via an operation unit such as a keyboard or mouse of the computer, sets the first threshold TH1 and the second threshold TH2, and presses the search button 210. This starts a search using the set conditions.

[0071] As shown in FIG. 14, when outputting the solution a12 of the similar past assignment a11, the output unit 14 also outputs the relevance k1 between the estimated category and the new assignment i1. The output unit 14 also outputs, as reference information, the multiple categories with the highest relevance levels with respect to the new assignment i1 that are less than a first threshold TH1, and their relevance levels k2. This allows the user to check the relevance levels k2 of the categories into which the new assignment i1 was not estimated to be classified, and determine whether the first threshold TH1 is appropriate. Note that, as reference information, it is also possible to output only the category with the highest relevance level and its relevance level among the categories with relevance levels less than the first threshold.

[0072] When outputting the solution a12 of the similar past assignment a11, the output unit 14 also outputs the similarity k3 between the new assignment i1 and the similar past assignment a11. Furthermore, the output unit 14 outputs, as reference information, the past assignment a11 with the highest similarity k3 to the new assignment i1 whose similarity k3 is less than the second threshold TH2 and its similarity k4. This allows the user to check the similarity k4 of the past assignment a11 that was not extracted and determine whether the second threshold TH2 is appropriate. Note that, among the past assignments with similarity less than the second threshold, only the past assignment with the highest similarity and its relevance may be output as reference information.

[0073] The input unit 11 is configured to be able to accept changes to the first threshold TH1 and the second threshold TH2 even after outputting the solution a12 for the similar past problem a11. For example, when a screen such as that shown in Fig. 14 is displayed on the computer operated by the user, the user resets the first threshold TH1 and the second threshold TH2 via an operation unit such as the computer's keyboard or mouse, and presses the search again button 220. This starts a search again using the set conditions.

[0074] As described above, the output unit 14 outputs the degree of association k1 between the estimated category and the new task i1, so the user can understand the degree of association k1 between the estimated category and the new task i1.

[0075] Furthermore, the output unit 14 outputs the relevance k2 of the category with the highest relevance among the multiple categories whose relevance with the new assignment i1 is less than a first threshold TH1. The input unit 11 is configured to be able to accept changes to the first threshold TH1. Therefore, the user can determine whether the first threshold TH1 is an appropriate value, and change the value of the first threshold TH1 as necessary to increase or decrease the number of categories into which the new assignment i1 is estimated to be classified.

[0076] The search unit 13 also outputs the similarity k3 between the extracted similar past assignment a11 and the new assignment i1, allowing the user to understand the similarity k3 between the extracted past assignment a11 and the new assignment i1.

[0077] Furthermore, the output unit 14 outputs the similarity k4 of the past assignment a11 with the greatest similarity among the multiple past assignments a11 whose similarity to the new assignment i1 is less than the second threshold TH2. The input unit 11 can also accept changes to the second threshold TH2. Therefore, the user can determine whether the second threshold TH2 is an appropriate value, and change the value of the second threshold TH2 as necessary to increase or decrease the number of similar past assignments a11 to be extracted.

[0078] <Third embodiment> Next, a third embodiment will be described. FIG. 15 is a diagram showing a method for determining a problem tag in the solution proposal system according to this embodiment. In the first embodiment, the assignment tag c4 for the past assignment a11 was determined based on the past assignment a11 and the information entered in the item of the item that has a parent-child relationship with the past assignment a11 in the hierarchical data D1. In contrast, in the third embodiment, the assignment tag c4 for the past assignment a11 is determined based on the past assignment a11 and the information related to the past assignment a11 in the domain 300 to which the past assignment a11 belongs in the hierarchical data D1.

[0079] As in the first embodiment, multiple hierarchical data D1 are provided from multiple domains 300. Therefore, in the multiple hierarchical data D1, each past assignment a11 belongs to one of the domains 300. As shown in FIG. 15, when determining the assignment tag c4 for the past assignment a11, “Check the quality of incoming goods,” belonging to a certain domain 300, the tag determination unit 21 first extracts information related to the past assignment a11 within the same domain 300 from the multiple hierarchical data D1. The extracted information is not particularly limited, but may include, for example, a sentence entered in assignment item a1, a sentence entered in means item a2, or both sentences entered in assignment item a1 and means item a2. In FIG. 15, for example, a sentence entered in assignment item a1, “Suppress variation by changing the production process or recipe,” and a sentence entered in assignment item a1, “Implement sampling inspections for redundant inspections and reliability,” are extracted as related information.

[0080] The method for extracting information related to the past assignments a11 is not particularly limited, but examples include a mechanical method using a text vectorization tool D6 such as word2vec, a manual method in which an expert extracts related information, or a combination of a mechanical method and a manual method. When the vectorization tool D6 is used, information that belongs to the same domain 300 and is close in semantic space is extracted from multiple hierarchical data D1.

[0081] The subsequent steps are the same as in the first embodiment, where words are extracted from the sentences "check the quality of incoming goods," "reduce variability by changing the production process or recipe," and "implement sampling checks for redundant inspections and reliability," and synonyms of the extracted words are added to determine the final issue tag c4.

[0082] As explained above, the information used to determine the assignment tag c4 of past assignment a11 in the hierarchical data D1 is not particularly limited to the information entered in an item that has a parent-child relationship with the assignment item a1 into which the past assignment a11 was entered, but is not particularly limited as long as it belongs to the same domain as the domain to which the past assignment a11 belongs in the hierarchical data D1 and is information related to the past assignment a11.

[0083] <Fourth embodiment> Next, a fourth embodiment will be described. FIG. 16 is a diagram showing past data according to this embodiment. In the first, second, and third embodiments, a past assignment a11 is input, and the past data used to determine the assignment tag c4 is hierarchical data D1. In contrast, in this embodiment, a past assignment a11 is input, and the past data used to determine the assignment tag c4 is table data D41.

[0084] The table data D41 is tabular data in which multiple past assignments a11 are linked to multiple solution methods a12. In this case, the assignment tag c4 of the past assignment a11 is determined based on the past assignment a11 and information in the table data D41 that belongs to the same domain 300 as the past assignment a11 and is related to the past assignment a11, as in the third embodiment. For example, when determining the assignment tag c4 of the past assignment a11 "check the quality of incoming products" that belongs to a certain domain 300, the past assignment a11 "suppress variation by changing the production process or recipe" and the past assignment a11 "implement sampling inspections for redundant inspections and reliability" are extracted as related information, as in the third embodiment. However, as in the third embodiment, the solution method a12 may also be extracted as related information.

[0085] As explained above, past assignments a11 are input, and the past data used to determine assignment tag c4 is not limited to hierarchical data D1, but may be data in other formats such as table data D41, as long as the past assignments a11 are linked to solution means a12.

[0086] Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, and are also included in the scope of the invention and its equivalents as defined in the claims. [Explanation of symbols]

[0087] 1: Proposed system 2: Generation system 11: Input section 12: Estimation part 13: Search section 14: Output section 21: Tag determination section 22: Data Creation Department 23: Model generation unit D1: Hierarchical data (historical data) D2: Set data D3: Ontology D4: Training data D5: Classification model D6: Vectorization Tools D41:Table data M: Relevance Matrix V: vertical vector a0: Target item a1: Assignment item a11: Past assignments a2: Means item a12: Solution b1: Parent item b2:Child item c1: Extract word c2:Synonym c3:Representative word c4:Issue tags g:word group h:Issue tags i1: New assignment i2: partial word i3, k1, k2: relevance k3, k4: Similarity TH1: First threshold TH2: Second threshold

Claims

1. It runs on a computer acquiring new assignments; using a classification model to estimate a category among a plurality of categories into which the new task will be classified; A step of searching for a past assignment that is classified into the plurality of categories and is similar to the new assignment and that is classified into the estimated category from among the plurality of past assignments; outputting solutions associated with the searched similar past problems; Equipped with In the step of estimating a category into which the new assignment will be classified, a category among the plurality of categories whose relevance to the new assignment is equal to or greater than a first threshold is estimated as the category into which the new assignment will be classified; In the step of outputting the solution, a degree of association between the estimated category and the new problem is output; In the step of outputting the solution, a degree of relevance of a category, among the plurality of categories, whose degree of relevance to the new problem is less than the first threshold is output; A method proposed by the solution means, in which the first threshold value can be changed by a user.

2. In the step of searching for similar past assignments, past assignments that are classified into the estimated category from among the plurality of past assignments and have a similarity to the new assignment that is equal to or greater than a second threshold are extracted as the similar past assignments; 2. The method for proposing a solution according to claim 1, wherein the step of outputting the solution comprises outputting a similarity between the extracted similar past problem and the new problem.

3. A program executed by a computer, acquiring new assignments; using a classification model to estimate a category among a plurality of categories into which the new task will be classified; A step of searching for a past assignment that is classified into the plurality of categories and is similar to the new assignment and that is classified into the estimated category from among the plurality of past assignments; outputting solutions associated with the searched similar past problems; Equipped with In the step of searching for similar past assignments, past assignments that are classified into the estimated category from among the plurality of past assignments and have a similarity to the new assignment that is equal to or greater than a second threshold are extracted as the similar past assignments; In the step of outputting the solution, a similarity between the extracted similar past problem and the new problem is output; In the step of outputting the solution, a similarity of a past assignment that is classified into the estimated category and has a similarity to the new assignment that is less than the second threshold is output from among the plurality of past assignments; The second threshold value can be changed by the user.

4. A program executed by a computer, acquiring new assignments; using a classification model to estimate a category among a plurality of categories into which the new task will be classified; A step of searching for a past assignment that is classified into the plurality of categories and is similar to the new assignment and that is classified into the estimated category from among the plurality of past assignments; outputting solutions associated with the searched similar past problems; Equipped with In the past data in which a plurality of solutions are linked to the plurality of past problems, each of the past problems belongs to one of a plurality of domains; The classification model has been trained using training data; The teacher data is data in which assignment tags corresponding to the plurality of past assignments are classified into the plurality of categories according to their mutual relevance, A method for proposing a solution, in which each of the problem tags is determined based on each of the past problems and information in the past data that belongs to the domain to which each of the past problems belongs among the multiple domains and is related to each of the past problems.

5. The past data includes hierarchical data in which problem items and means items are arranged in a hierarchical structure, 5. The method for proposing a solution according to claim 4, wherein each of the past assignments is entered in one of the assignment items in the hierarchical data.

6. It runs on a computer an input unit for accepting input of a new assignment; an estimation unit that estimates a category into which the new assignment will be classified from among a plurality of categories into which a plurality of past assignments have been classified using a classification model; a search unit that searches for past assignments similar to the new assignment among the plurality of past assignments within the estimated category; an output unit that outputs solutions associated with the searched similar past problems; Equipped with the estimation unit estimates, from among the plurality of categories, a category having a degree of relevance with the new assignment equal to or greater than a first threshold as a category into which the new assignment will be classified; the output unit outputs the estimated degree of association between the category and the new task; the output unit outputs a degree of relevance of a category, among the plurality of categories, whose degree of relevance with the new assignment is less than the first threshold; The system for proposing the solution, wherein the input unit is capable of accepting a change to the first threshold value.

7. the search unit extracts, from the plurality of past assignments, past assignments that are classified into the estimated category and have a similarity to the new assignment that is equal to or greater than a second threshold, as the similar past assignments; The system for proposing solutions according to claim 6 , wherein the output unit outputs a similarity between the extracted similar past assignment and the new assignment.

8. the output unit outputs a similarity of a past assignment among the plurality of past assignments whose similarity to the new assignment is less than the second threshold; The system for proposing the solution according to claim 7 , wherein the input unit is capable of accepting a change to the second threshold value.

9. In the past data in which a plurality of solutions are linked to the plurality of past problems, each of the past problems belongs to one of a plurality of domains; The classification model has been trained using training data; The teacher data is data in which assignment tags corresponding to the plurality of past assignments are classified into the plurality of categories according to their mutual relevance, A solution proposal system according to any one of claims 6 to 8, wherein each of the assignment tags is determined based on each of the past assignments and information in the past data that belongs to the domain to which each of the past assignments belongs among the multiple domains and is related to each of the past assignments.

10. A method executed on a computer, an input unit for accepting input of a new assignment; an estimation unit that estimates a category into which the new assignment will be classified from among a plurality of categories into which a plurality of past assignments have been classified using a classification model; a search unit that searches for past assignments similar to the new assignment among the plurality of past assignments within the estimated category; an output unit that outputs solutions associated with the searched similar past problems; Equipped with In the past data in which a plurality of solutions are linked to the plurality of past problems, each of the past problems belongs to one of a plurality of domains; The classification model has been trained using training data; The teacher data is data in which assignment tags corresponding to the plurality of past assignments are classified into the plurality of categories according to their mutual relevance, A solution suggestion system in which each of the problem tags is determined based on each of the past problems and information in the past data that belongs to the domain to which each of the past problems belongs among the multiple domains and is related to each of the past problems.

11. The past data includes hierarchical data in which problem items and means items are arranged in a hierarchical structure, 11. The system for proposing solutions according to claim 10, wherein each of the past assignments is entered in one of the assignment items in the hierarchical data.

Images