Information processing device, data set, operation method of information processing device, and program

The information processing device facilitates a precise and efficient search for multi-component composition prescriptions by utilizing a vector space analysis of raw material contents, addressing the inefficiencies and overfitting issues in existing methods.

JP2024159258APending Publication Date: 2024-11-08KOSE CORPORATION
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023075126
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing methods for inferring causal relationships between prescriptions and characteristic values in multi-component compositions require significant training data, which is time-consuming and costly, and are prone to overfitting, necessitating a more efficient and accurate search method.

Method used

An information processing device that utilizes a storage unit to store information on multiple prescriptions and their corresponding cosmetic characteristics, selecting a second prescription with a predetermined distance in a vector space formed by raw material contents, and outputs information on the selected prescription and its characteristics.

Benefits of technology

Enables a simple and highly precise search for formulations by reducing the need for training data and minimizing overfitting, allowing for quicker identification of desired characteristic values.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024159258000001_ABST
    Figure 2024159258000001_ABST
Patent Text Reader

Abstract

To provide an information processing device, a data set, an operation method of the information processing device, and a program for easily and accurately searching for formulations of cosmetics.SOLUTION: In an information processing system 1 having a server device 10 and a terminal device 12 connected so as to enable information communication with each other via a network 11, the terminal device 12 includes a storage unit that stores information on a plurality of formulations, each of which includes the content of a plurality of raw materials, and information on the characteristics of a cosmetic corresponding to each formulation, and a control unit that selects, from the plurality of formulations, a second formulation that indicates a predetermined distance from a first formulation that is different from any of the plurality of formulations in a vector space whose components are the content of the plurality of raw materials, and outputs information on the second formulation and the characteristics of the cosmetic corresponding to the second formulation.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to an information processing device dataset, an information processing device operation method, and a program. [Background technology]

[0002] In the development of multi-component compositions such as cosmetics, the characteristic values ​​of multiple prototypes produced with different recipes are measured to search for and identify recipes that will give characteristic values ​​that ensure the desired quality. Since there are many different recipes for multi-component compositions, a large number of steps are required to search for a recipe that will give the desired characteristic values. As an example of a technology that supports such a process, Patent Document 1 discloses a technology that infers the causal relationship between product specifications and product characteristics and presents it to the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2021-144481 A Summary of the Invention [Problem to be solved by the invention]

[0004] A huge amount of training data is required to machine-learn the causal relationship between a prescription and the characteristic values ​​of a composition. However, it takes a lot of time and cost to collect and organize such training data. Even if training data can be prepared, overlearning may cause the causal relationship to be inferred appropriately. Therefore, a simple and highly accurate method for formula search is required.

[0005] In view of the above, the following describes an information processing device and the like for easily and highly accurately searching for a formulation for a multi-component composition. [Means for solving the problem]

[0006] In order to solve the above problems, the information processing device of the present disclosure has a memory unit that stores information on a plurality of formulations, each of which includes the content of a plurality of raw materials, and information on the characteristics of the cosmetic corresponding to each formulation, and a control unit that selects a second formulation from the plurality of formulations, the second formulation being different from any of the plurality of formulations, and having a predetermined distance in a vector space having the contents of the plurality of raw materials as components, and outputs information on the second formulation and the characteristics of the cosmetic corresponding to the second formulation.

[0007] Another aspect of the present disclosure is a dataset stored in an information processing device, the dataset including information on a plurality of formulations each including a content of a plurality of ingredients, information on the properties of the cosmetic corresponding to each formulation, and information on a classification determined based on the degree to which each of the ingredients in each formulation contributes to the properties of the cosmetic corresponding to the formulation, and causes the information processing device to execute the steps of: selecting a second formula from the plurality of formulations, the second formula being different from any of the plurality of formulations, and having a predetermined distance in a vector space having the contents of the plurality of ingredients as components, and in which an ingredient in the same classification as an ingredient having a predetermined content in the first formula has the predetermined content; and outputting information on the second formula and information on the properties of the cosmetic corresponding to the second formula.

[0008] Yet another aspect of the present disclosure is a method of operating an information processing device, the method including the steps of: storing information on a plurality of formulations, each of which includes a content of a plurality of ingredients, and information on the properties of the cosmetic corresponding to each formulation; selecting a second formulation from the plurality of formulations, the second formulation being different from any of the plurality of formulations, and having a predetermined distance in a vector space having the contents of the plurality of ingredients as components; and outputting information on the second formulation and the properties of the cosmetic corresponding to the second formulation.

[0009] Yet another aspect of the present disclosure is a program, wherein the program is executed on an information processing device that stores information on a plurality of formulations, each of which includes the content of a plurality of raw materials, and information on the characteristics of the cosmetic corresponding to each formulation, so that the information processing device executes a process of selecting a second formulation from the plurality of formulations, the second formulation being a first formulation different from any of the plurality of formulations, and having a predetermined distance in a vector space having the contents of the plurality of raw materials as components, and outputting information on the second formulation and the characteristics of the cosmetic corresponding to the second formulation. Effect of the Invention

[0010] According to the operation method of the information processing device and the like of the present disclosure, it becomes possible to easily and highly accurately search for a formula for a multi-component composition. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 illustrates an example of a configuration of an information processing system. [Diagram 2] FIG. 1 is a diagram illustrating a reference prescription and a target prescription. [Diagram 3] FIG. 11 is a flowchart illustrating an example of an operation procedure of the information processing system. [Figure 4] FIG. 13 is a diagram showing a display example of similar prescriptions. [Diagram 5] FIG. 13 is a diagram illustrating a modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described.

[0013] [System Overview] FIG. 1 is a diagram showing a configuration example of an information processing system in an embodiment. The information processing system 1 has a server device 10 and a terminal device 12 connected to each other so as to be able to communicate information with each other via a network 11. The server device 10 is one or more server computers. The server device 10 may be a single computer, or may be a plurality of computers that execute the operations in this embodiment in cooperation with each other to provide a cloud service. The terminal device 12 is one or more information processing devices such as a personal computer, a tablet terminal device, etc. The terminal device 12 may include a smartphone, etc. The network 11 is, for example, a LAN (Local Area Network), the Internet, an ad-hoc network, a MAN (Metropolitan Area Network), a mobile communication network, or other networks, or any combination thereof.

[0014] The information processing system 1 assists in the search for a formula that will give a desired characteristic value in the development of a multi-component composition. A multi-component composition is a composition produced from multiple raw materials, and is produced by mixing various raw materials in any amount. In the following, a cosmetic product, for example eye shadow among makeup cosmetics, is used as an example of a multi-component composition. Eye shadow is required to have a certain degree of rigidity as a product. Here, a load value is used as the characteristic value indicating rigidity. The information processing system 1 assists in the search for a formula that will give the desired load value of the cosmetic product, that is, a combination of multiple raw materials to be mixed and their amounts, in the development of a cosmetic product, i.e., an eye shadow product.

[0015] The server device 10 has a storage unit 102 and a control unit 103, and corresponds to the "information processing device" of this embodiment. The storage unit 102 stores information on a plurality of recipes (hereinafter referred to as reference recipes) each including the content of a plurality of raw materials, and information on the properties of the cosmetic corresponding to each reference recipe, i.e., the property values. The control unit 103 selects a recipe (hereinafter referred to as similar recipe) that is a predetermined distance from a recipe (hereinafter referred to as target recipe) different from any of the plurality of reference recipes in a vector space having the content of a plurality of raw materials as components, from among the plurality of reference recipes, and outputs the similar recipe information and the property values ​​of the cosmetic corresponding to the similar recipe. The operator can confirm whether the property values ​​expected from the target recipe are close to the property values ​​of the similar recipe. Once the approximation is confirmed, it is possible to search for a recipe (hereinafter referred to as target recipe) that can secure the desired property values ​​by fine-tuning the target recipe. Therefore, compared to the case where the property values ​​are measured one by one while randomly changing the target recipe to search for the target recipe, it is possible to shorten the process of recipe search and identify the target recipe earlier. Furthermore, there is no need to prepare training data for machine learning. Therefore, cosmetic formulation search can be carried out easily and with high accuracy.

[0016] Next, the configurations of the server device 10 and the terminal device 12 will be described.

[0017] The server device 10 includes a communication unit 101, a storage unit 102, and a control unit 103. When the server device 10 is configured with two or more computers, these components are appropriately arranged in the two or more computers.

[0018] The communication unit 101 includes one or more communication interfaces. The communication interface is, for example, a LAN interface. The communication unit 101 receives information used in the operation of the server device 10, and transmits information obtained by the operation of the server device 10. The server device 10 is connected to a network 11 by the communication unit 101, and communicates information with a terminal device 12 via the network 11.

[0019] The storage unit 102 includes, for example, one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these, functioning as a main storage device, an auxiliary storage device, or a cache memory. The semiconductor memory is, for example, a random access memory (RAM) or a read only memory (ROM). The RAM is, for example, a static RAM (SRAM) or a dynamic RAM (DRAM). The ROM is, for example, an electrically erasable programmable ROM (EEPROM). The storage unit 102 stores information used in the operation of the control unit 103 and information obtained by the operation of the control unit 103.

[0020] The control unit 103 includes one or more processors, one or more dedicated circuits, or a combination of these. The processor includes, for example, a general-purpose processor such as a central processing unit (CPU), or a dedicated processor specialized for a specific process such as a graphics processing unit (GPU). The dedicated circuit includes a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc.

[0021] The functions of the server device 10 are realized by a processor included in the control unit 103 executing a control program. The control program is a program for causing the processor to function as the control unit 103. Also, some or all of the functions of the server device 10 may be realized by a dedicated circuit included in the control unit 103. Also, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 103, and the control unit 103 may read it from the medium.

[0022] The terminal device 12 includes a communication unit 121 , a storage unit 122 , a control unit 123 , an input unit 125 , and an output unit 126 .

[0023] The communication unit 121 has a communication module compatible with a wired or wireless LAN standard, a module compatible with a mobile communication standard such as LTE, 4G, 5G, etc. The terminal device 12 is connected to the network 11 by the communication unit 121 via a nearby router device or a mobile communication base station, and performs information communication with the server device 10 via the network 11.

[0024] The memory unit 122 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these. The semiconductor memories are, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The memory unit 122 functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The memory unit 122 stores information used in the operation of the control unit 123 and information obtained by the operation of the control unit 123.

[0025] The control unit 123 has, for example, one or more general-purpose processors such as a CPU, an MPU (Micro Processing Unit), or one or more dedicated processors such as a GPU specialized for a specific process. Alternatively, the control unit 123 may have one or more dedicated circuits such as an FPGA, an ASIC, or the like. The control unit 123 generally controls the operation of the terminal device 12 by operating according to a control / processing program, or operating according to an operating procedure implemented as a circuit. The control unit 123 transmits and receives various information to and from the server device 10, etc. via the communication unit 121, and executes the operation according to this embodiment.

[0026] The functions of the terminal device 12 are realized by a processor included in the control unit 123 executing a control program. The control program is a program for causing the processor to function as the control unit 123. Also, some or all of the functions of the terminal device 12 may be realized by a dedicated circuit included in the control unit 123. Also, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 123, and the control unit 123 may read it from the medium.

[0027] The input unit 125 includes one or more input interfaces. The input interfaces include, for example, physical keys, capacitive keys, a pointing device, and a touch screen that is integrated with a display. The input unit 125 accepts an operation to input information used for the operation of the control unit 123, and sends the input information to the control unit 123.

[0028] The output unit 126 includes one or more output interfaces. The output interfaces include, for example, a display and a speaker. The display is, for example, an LCD or an organic EL display. The output unit 126 outputs information obtained by the operation of the control unit 123.

[0029] In the server device 10 and the terminal device 12, the control units 103 and 123 transmit and receive information to each other via the communication units 101 and 121, respectively, and execute information processing to realize their respective functions. In the server device 10 and the terminal device 12, information to be processed or processed / generated by the control units 103 and 123, respectively, is appropriately stored in the storage units 102 and 122. In the terminal device 12, the input unit 125 accepts an operation by the operator and sends information corresponding to the operation to the control unit 123, and the output unit 126 outputs the information sent from the control unit 123 to the operator by displaying or the like.

[0030] Next, the reference formulation and the control formulation will be described.

[0031] [Reference prescription and target prescription] 2 shows examples of reference and target prescriptions. Tables 20 and 21 show examples of reference prescriptions, and table 22 shows an example of a target prescription.

[0032] Table 20 shows reference recipes Ri (i is a natural number) which are combinations of amounts of a plurality of raw materials Mn (n is a natural number). The number of raw materials Mn can be, for example, 100 to several hundreds. The numerical value corresponding to each raw material Mn for each reference recipe Ri indicates the content (mass percent), and the numerical value "0" indicates that the raw material Mn is not contained. The raw materials Mn are divided into four categories, namely "pearl / glitter", "pigment", "body powder", and "other". Such classifications are predefined based on the criterion that the degree of contribution of each raw material to the characteristic value of the cosmetic, i.e., the load value, is the same. For example, an operator sets a provisional classification for each desired physical property value, and verifies that the raw materials for each provisional classification have the same degree of contribution to the physical property value to confirm the classification. The number of classifications can be set arbitrarily. The classifications may be further subdivided, for example, as shown in Table 21. Furthermore, each reference recipe Ri is associated with a "load value" as the characteristic value of the cosmetic obtained in each case. Such reference recipes Ri and load values ​​are obtained by producing prototypes in advance according to each reference recipe Ri and measuring the load values ​​of each prototype.

[0033] Table 21 shows examples of sub-categories according to the judgment criteria for each of the categories "pearl glitter", "pigment" and "extender powder". The sub-categories are arbitrary classifications according to the levels of all components, particle size, color, viscosity, etc. For example, the category "pearl glitter" is subdivided into five levels according to the judgment criteria "all components", "color" and "particle size". That is, the category "pearl glitter" is subdivided into levels 1 to 5 according to whether the base and coating in "all components" are the same or not, whether the "color" is the same or interference or colored, and on the condition that the "particle size" is approximately the same. Also, for example, the category "pigment" is subdivided into two levels according to the judgment criteria "all components" and "color". That is, the category "pigment" is subdivided into levels 1 to 2 according to whether the "all components" and "color" are the same or not. Furthermore, for example, the category "extender powder" is subdivided into two levels according to the judgment criteria "all components", "particle size" and "shape". In other words, the classification "extender powder" is subdivided into levels 1 and 2, depending on whether "all ingredients" are the same or not, under the condition that "particle size" and "shape" are similar and identical, respectively. Here, the combination of raw material classifications can be obtained in 20 different ways, for example, by combining the five levels of the classification "pearl / glitter," the two levels of the classification "pigment," and the two levels of the classification "extender powder." If unclassified raw materials are added to this, 21 different classification combinations are possible.

[0034] Table 22 shows a target recipe Rt that is a combination of a reference recipe and the amounts of multiple common raw materials Mn (n is a natural number) that are not included in the reference recipe Ri. The numerical value corresponding to each raw material Mn in the target recipe Rt indicates the content (mass percent), and the numerical value "0" indicates that the raw material Mn is not contained.

[0035] Next, a procedure for searching for a similar prescription to the target prescription from the reference prescription as described above will be described.

[0036] [Example of operation of information processing system 1] Fig. 3 is a flow chart for explaining an example of an operation procedure of the information processing system 1. The operation procedure in Fig. 3 is an operation procedure for searching for a similar prescription.

[0037] In step S30, the control unit 103 of the server device 10 acquires information on the target prescription. For example, when the operator inputs information on the target prescription to the terminal device 12, the terminal device 12 sends information on the target prescription to the server device 10. The terminal device 12 acquires information on the reference prescription from the server device 10, for example, and displays a list of names of ingredients included in the reference prescription to prompt the operator to make a selection. When the operator arbitrarily selects ingredients and executes an operation to set the amount of each ingredient, the terminal device 12 sends information on the selected ingredients and their amounts to the server device 10. Alternatively, the operator may arbitrarily design ingredients of the target prescription and the amounts of each ingredient in advance, and send the designed target prescription from the terminal device 12 to the server device 10, which acquires it.

[0038] In step S31, the control unit 103 of the server device 10 derives a similar prescription. The control unit 103 selects a similar prescription from among a plurality of reference prescriptions, which has a predetermined distance from the target prescription in a vector space having the contents of a plurality of raw materials as components. The control unit 103 derives the distance from the target prescription Rt to each of the reference prescriptions Ri shown in table 20 in a vector space having the contents of each of the raw materials Mn as components. Such a distance is, for example, cosine similarity, Euclidean distance, etc. Here, cosine similarity is used. The cosine similarity Cosθ between the reference prescription Ri and the target prescription Rt is derived by the following formula 1. TIFF2024159258000002.tif52170

[0039] The cosine similarity takes a value greater than 0 and less than or equal to 1, and the greater the value, the closer the distance in the vector space. The cosine similarity is advantageous in that it is possible to evaluate the similarity of the formula without having to consider the difference in magnitude (absolute value) between the vectors, since it calculates the angle between the vectors. The control unit 103 selects an arbitrary number (e.g., 5) of the cosine similarities obtained by the above formula 1 in ascending order, thereby selecting a similar formula corresponding to the selected cosine similarity. At this time, the control unit 103 may select a predetermined number of similar formulas in descending order of cosine similarity, on the condition that a raw material in a common classification with a raw material having an arbitrary reference content (e.g., a content of 0 to 0.1 mass percent at the resolution at the time of measurement) in the target formula has a reference content. In this way, it is possible to suppress the deviation of the load value of the cosmetic produced by the target formula from the load value corresponding to the similar formula.

[0040] In step S32, the control unit 103 outputs information on the similar recipe. For example, the server device 10 sends the information on the similar recipe to the terminal device 12, and the terminal device 12 displays the information on the similar recipe to the operator. The operator can search for raw material candidates that are likely to obtain the desired characteristic value, that is, that have a large effect on the characteristic value.

[0041] FIG. 4 is a diagram showing an example of the display of similar formulas. Table 40 shows a list of the top five target formulas similar to the target formula. Table 40 includes the items of "rank" of the similarity of the similar formula, "product number" and "product name" of the cosmetic produced by the similar formula, "formula identification number" of the similar formula, "weighted value" of the cosmetic produced by the similar formula and its evaluation, and "similarity" showing the value of cosine similarity. The values ​​of each item of the similar formulas ranked 1st to 5th in similarity are shown. Here, it is shown that the "weighted value" 45N of the similar formula ranked 2nd is insufficient and the "weighted value rank" is judged to be NG. It is shown that the other similar formulas are judged to be OK because the "weighted value" is sufficient. With such a display, the operator can confirm whether the characteristic value expected of the target formula is close to the characteristic value of the similar formula. Once the closeness is confirmed, it becomes possible to search for the target formula by fine-tuning the target formula. Furthermore, the server device 10 may derive the average, median, or the like of the weighted values ​​of similar recipes and output them to the operator, allowing the operator to refer to more information when searching for an optimal recipe.

[0042] The control unit 103 can limit the range of the reference recipe for searching for the optimum recipe by an arbitrary index. Such an index is, for example, the average of the differences between the measured physical property values ​​of the target recipe and the physical property values ​​of each reference recipe. When the measured physical property values ​​of the target recipe are input, the control unit 103 calculates the average of the differences from each reference recipe. Then, steps S31 and S32 are executed for reference recipes whose differences are equal to or less than the average. In this way, by limiting the range of the reference recipe to a certain extent to a range that is highly likely to be similar, it becomes possible to search for the optimum recipe more efficiently.

[0043] [Variation 1] In one modified example, the reference formula and the target formula further include information on the production conditions of the corresponding cosmetic in addition to the information on the raw materials. The production conditions are, for example, the manufacturing process of the cosmetic, the type of container in which the cosmetic is filled, the filling method, the filling amount, the pressure of the press, the type of equipment for mixing the raw materials, etc. More specifically, for example, the type of the container includes the material of the container, the shape of the container, the size of the container (lateral direction), the depth of the container, etc., and the filling method includes dry press filling, slurry filling, etc. The control unit 103 of the server device 10 may select a predetermined number of similar formulas in descending order of cosine similarity, on the condition that the reference information has the same production conditions as the target formula. Considering the possibility that the load value of the cosmetic is influenced not only by the selection and content of the raw materials but also by the production conditions, by selecting a similar formula with the same production conditions, it is possible to further suppress the deviation of the load value of the cosmetic produced by the target formula from the load value corresponding to the similar formula.

[0044] [Set reference prescription] The reference formula is stored in the storage unit 102 by an operator measuring the load value of the cosmetic generated based on each reference formula in advance, associating the measured value with the reference formula, and sending it from the terminal device 12 to the server device 10. At this time, the operator may add classification information to the reference formula using the terminal device 12. The operator assigns classification information to each ingredient included in the reference formula according to the degree of contribution to the load value of the cosmetic. Alternatively, after setting the information of the reference formula in the server device 10, the terminal device 12 may obtain the information of the reference formula and display a list of ingredients of the reference formula, and the operator may assign classification information to the list of ingredients.

[0045] The control unit 103 can update the information of the reference prescription by adding the derived optimum prescription as a new reference prescription. In such a case, the more newly added the reference prescription, the more existing reference prescriptions are targeted at the time of optimum prescription search. Therefore, the variation of similar prescriptions in the vector space becomes smaller. Therefore, when limiting the range of the reference prescription for searching the optimum prescription by the average of the physical property value, the control unit 103 limits the target for calculating the average to the most recent reference prescription. For example, when searching for the 1001st optimum prescription, the most recent 900 reference prescriptions are targeted among the existing 1000 reference prescriptions. This makes it possible to search for the optimum prescription more efficiently by targeting a range where the reference prescription is more likely to be similar.

[0046] [Variation 2] Another modified example relates to a case where a formula search is performed using different reference formulas depending on the type of cosmetic. FIG. 5 shows an example of the master table of the table 20 shown in FIG. 2. In this master table 50, the type of cosmetic, characteristic values, and reference formula table IDs are stored in association with each other. The characteristic values ​​to be pursued in relation to the quality of the product differ depending on the cosmetic. For example, the load value for ensuring the rigidity of makeup cosmetics such as eye shadow and lipstick is evaluated. On the other hand, the viscosity of basic cosmetics such as emulsion and cream is evaluated. The server device 10 stores such a master table 50 in the storage unit 102 and presents it to the operator via the terminal device 12. For example, when the operator selects the type of cosmetic to be developed, the server device 10 refers to the reference formula table corresponding to the selected cosmetic. For example, when the operator selects eye shadow, the server device 10 refers to the reference formula table 20 and executes the steps of FIG. 3. Alternatively, when emulsion or cream is selected, the reference formula table previously stored in the server device 10 corresponding to emulsion or cream is referred to. In such a reference recipe, the combination of ingredients and their contents for producing a milky lotion or cream is stored in association with the viscosity obtained in each case. In addition, each ingredient is pre-classified into categories such as "polymer," "surfactant," and "higher alcohol" according to the degree to which it contributes to the viscosity. In this way, it is possible to easily and highly accurately search for the optimal recipe according to the type of cosmetic product to be developed.

[0047] In addition to the above-mentioned examples, the present embodiment may be applicable to various cosmetics. The cosmetics may be, for example, makeup cosmetics such as mascara, lip gloss, eyeliner, foundation, face color, concealer, makeup base, makeup keep mist, etc., basic cosmetics such as lotion, beauty essence, pack, all-in-one gel, body milk, face wash, oil cleanser, cleansing cream, cleansing liquid, sunscreen, antiperspirant, etc., hair cosmetics such as shampoo, rinse, conditioner, hair treatment, styling water, hair wax, hair dye, hair growth agent, etc. Furthermore, the raw materials used to produce each cosmetic include, for example, powders, aqueous components, alcohols, water-soluble polymers, film-forming agents, UV absorbers, silicone oils, hydrocarbon oils, ether oils, ester oils, natural animal and vegetable oils and semi-synthetic oils, emollients, anionic surfactants, nonionic surfactants, cationic surfactants, amphoteric surfactants, gelling agents and thickeners, anti-fading agents, antioxidants, defoamers, cosmetic ingredients (skin whitening agents, cell activators, anti-inflammatory agents, blood circulation promoters, skin astringents, antiseborrheic agents, etc.), preservatives, antibacterial agents, fragrances, vitamins, amino acids, nucleic acids, hormones, etc. Furthermore, this embodiment can also be applied to multi-component compositions other than cosmetics, such as skin topicals, pharmaceuticals, foods, paints, detergents, etc.

[0048] The operation of the server device 10 as described above enables a simple and highly accurate formulation search in the development of cosmetics.

[0049] In the above, the processing / control program that specifies the operation of the server device 10 may be stored in a cloud server or the like and downloaded to the server device 10 via the network 11, or may be stored in a non-transitory recording / storage medium that is readable by a computer and read by the server device 10 from the medium.

[0050] The above-mentioned operation procedure is included in the scope of the present embodiment whether it is executed by one information processing device or whether some or all of each step is executed by multiple information processing devices. Furthermore, when multiple information processing devices are used, they may or may not be connected to each other so as to be able to communicate with each other. When multiple information processing devices are not connected to each other so as to be able to communicate with each other, the result of information processing by one information processing device may be shared with the other information processing devices by, for example, storing it in a storage medium and reading it out by the other information processing devices.

[0051] In the above, the embodiment has been described based on the drawings and examples, but it should be noted that those skilled in the art can easily make various modifications and corrections based on the present disclosure. Therefore, it should be noted that these modifications and corrections are included in the scope of the present disclosure. For example, the functions included in each means, each step, etc. can be rearranged so as not to be logically inconsistent, and multiple means, steps, etc. can be combined into one or divided into one. [Explanation of symbols]

[0052] 10: Server device 11: Network 12: Terminal device 101, 121: Communications Department 102, 122: Storage section 103, 123: control unit 125: Input section 126: Output section

Claims

1. a storage unit that stores information on a plurality of formulations, each of which includes the content of a plurality of raw materials, and information on the characteristics of the cosmetic material corresponding to each formulation; a control unit that selects, from among the plurality of formulations, a second formulation that is a predetermined distance from a first formulation that is different from any of the plurality of formulations in a vector space having the contents of the plurality of ingredients as components, and outputs information on the second formulation and the characteristics of the cosmetic material corresponding to the second formulation; An information processing device having the above configuration.

2. In claim 1, Each of the plurality of recipes includes classification information determined based on the degree to which each of the plurality of ingredients contributes to the characteristics of the cosmetic corresponding to the recipe; The second recipe has a predetermined content of a raw material of a common class with a raw material having a predetermined content in the first recipe. Information processing device.

3. In claim 2, The plurality of recipes each further includes information on the conditions for producing a corresponding cosmetic product; The second recipe has a common production condition with a production condition specified corresponding to the first recipe. Information processing device.

4. In claim 2, The classification of each of the plurality of raw materials varies according to the type of the characteristic, When the type of the characteristic is designated, the control unit selects the second prescription based on information of a classification according to the designated type of characteristic. Information processing device.

5. In claim 2, The classification information is stored in the storage unit by the control unit outputting information of each prescription, prompting the user to input the classification information, and acquiring the input information. Information processing device.

6. A data set stored in an information processing device, comprising: Information on a plurality of recipes each including a content of a plurality of ingredients; Information on the characteristics of the cosmetics corresponding to each formulation, and information on a classification determined based on the degree to which each of the plurality of ingredients in each formulation contributes to the characteristics of the cosmetic corresponding to the formulation; The information processing device includes: A step of selecting a second recipe from among the plurality of recipes, the second recipe being different from any of the plurality of recipes and having a predetermined distance in a vector space having the contents of the plurality of ingredients as components, and having the predetermined content of an ingredient of a common classification with an ingredient having the predetermined content in the first recipe; outputting information on the second formulation and information on the characteristics of the cosmetic corresponding to the second formulation; A dataset to run.

7. A method for operating an information processing device, comprising: storing information on a plurality of recipes, each of which includes the content of a plurality of raw materials, and information on the characteristics of the cosmetic corresponding to each recipe; selecting a second formulation from the plurality of formulations, the second formulation being a predetermined distance from a first formulation different from any of the plurality of formulations in a vector space having the contents of the plurality of ingredients as components, and outputting information on the second formulation and the characteristics of the cosmetic corresponding to the second formulation, A method for operating an information processing device.

8. The method is executed by an information processing device that stores information on a plurality of recipes, each of which includes the content of a plurality of raw materials, and information on the characteristics of the cosmetic corresponding to each recipe, so that the information processing device: selecting a second formula from the plurality of formulas, the second formula being a predetermined distance from a first formula different from any of the plurality of formulas in a vector space having the contents of the plurality of ingredients as components, and outputting information on the second formula and the characteristics of the cosmetic corresponding to the second formula; program.

Citation Information

Patent Citations

  • Design assistance system

    JP2021144481A