Method for generating service review and system therefor

Abstract

A method for generating a service review and a system therefor are provided. A method for generating a service review according to an embodiment of the present disclosure, the method being performed by a computing device, may include the steps of: obtaining a first service review having a similarity equal to or greater than a reference value by using user information and care information of a care service used by a user; obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the care service from a user terminal; inputting the first evaluation score and the second evaluation score in an emotion dictionary for a pre-generated care service evaluation item, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and inputting the first word set, the second word set, and the first service review to a generative AI model, and generating a second service review as a result of the input, wherein the user information includes basic information of a guardian and basic information of a patient, the care information includes disease information of the patient, and the first evaluation score is a value equal to or greater than the second evaluation score.

Description

Method and system for creating service reviews

[0001] The present disclosure relates to a method and system for generating service reviews. More specifically, the present disclosure relates to a method and system for automatically generating service reviews based on user input information.

[0002] A caregiver matching platform is an online service that connects patients, patients in need, or their guardians with suitable caregivers. It provides efficient and reliable care services through profile creation, matching algorithms, search and filtering, reviews and ratings, reservation and schedule management, and safety and authentication features.

[0003] Meanwhile, patients or guardians tend to find it cumbersome to write a review of the service after receiving care services on caregiver matching platforms.

[0004] Accordingly, a technology is required that allows patients or guardians to easily and conveniently enter reviews of nursing services.

[0005] A technical problem to be solved in some embodiments of the present disclosure is to provide a method and system for generating a service review that allows a patient or guardian to easily and conveniently input a service review for a nursing service.

[0006] Another technical problem to be solved in some embodiments of the present disclosure is to provide a service review generation method and system that automatically generates service reviews for nursing services.

[0007] The technical problems of the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art of the present disclosure from the description below.

[0008] In order to solve the above technical problem, a method for generating a service review according to an embodiment of the present disclosure is a method performed by a computing device, comprising: obtaining a first service review having a similarity level higher than a reference value by using user information and care information of a care service used by the user; obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the care service from a user terminal; inputting the first evaluation score and the second evaluation score into an emotion dictionary for previously generated care service evaluation items, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and inputting the first word set, the second word set, and the first service review into a generative AI model, and generating a second service review as a result of the input, wherein the user information includes basic information of a guardian and basic information of a patient, the care information includes disease information of the patient, and the first evaluation score may be a value greater than or equal to the second evaluation score.

[0009] In one embodiment, the step of obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score includes the steps of calculating a first weighted score for the first evaluation score and a second weighted score for the second evaluation score; and the steps of obtaining the first word set corresponding to the first weighted score and the second word set corresponding to the second weighted score, wherein the first weighted score is a value obtained by subtracting an average of the first evaluation score and the second evaluation score from the first evaluation score, and the second weighted score is a value obtained by subtracting the average from the second evaluation score, and the first word set may include as many positive words as the number corresponding to the first weighted score, and the second word set may include as many negative words as the number corresponding to the absolute value of the second weighted score.

[0010] In one embodiment, the generating step includes: receiving a request for modification of the generated second service usage review from the user terminal; in response to the received modification request, correcting the first evaluation score to obtain a first modified evaluation score and correcting the second evaluation score to obtain a second modified evaluation score; inputting the first modified evaluation score and the second modified evaluation score into the emotional dictionary, and obtaining a third word set corresponding to the first modified evaluation score and a fourth word set corresponding to the second modified evaluation score; and inputting the third word set, the fourth word set, and the first service usage review into the generative AI model, and regenerating the third service usage review as a result of the input, wherein the modification request may be at least one of a first option for increasing the first evaluation score and the second evaluation score by a first set value and a second option for decreasing the first evaluation score and the second evaluation score by the first set value.

[0011] In one embodiment, the step of obtaining a first corrected evaluation score by correcting the first evaluation score and obtaining a second corrected evaluation score by correcting the second evaluation score may include a step of setting the first corrected evaluation score to the maximum evaluation score when the first corrected evaluation score exceeds the maximum evaluation score for the first evaluation item.

[0012] In one embodiment, the step of obtaining a first corrected evaluation score by correcting the first evaluation score and obtaining a second corrected evaluation score by correcting the second evaluation score may include a step of setting the second corrected evaluation score to the minimum evaluation score when the second corrected evaluation score is less than the minimum evaluation score for the second evaluation item.

[0013] In one embodiment, the generating step includes: receiving a request for modification of the generated second service usage review from the user terminal; correcting the first evaluation score in response to the received modification request to obtain a first corrected evaluation score; inputting the first corrected evaluation score into the emotional dictionary and obtaining a third word set corresponding to the first corrected evaluation score; and inputting the third word set, the second word set, and the first service usage review into the generative AI model and regenerating the third service usage review as a result of the input, wherein the modification request may be at least one of a first option for increasing the first evaluation score by a first set value and a second option for decreasing the first evaluation score by the first set value.

[0014] In one embodiment, the step of correcting the first evaluation score to obtain a first corrected evaluation score may include the step of setting the first corrected evaluation score to the maximum evaluation score when the first corrected evaluation score exceeds the maximum evaluation score for the first evaluation item.

[0015] In one embodiment, the step of correcting the first evaluation score to obtain a first corrected evaluation score may include the step of setting the first corrected evaluation score to the minimum evaluation score when the first corrected evaluation score is less than the minimum evaluation score for the first evaluation item.

[0016] According to one embodiment of the present disclosure for solving the above technical problem, a system for generating a service review comprises: a communication interface; a memory on which a computer program is loaded; and one or more processors on which the computer program is executed, wherein the computer program comprises: an operation for obtaining a first service review having a similarity level higher than a reference value by using user information and care information of a care service used by the user; an operation for obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item with respect to the care service from a user terminal; an operation for inputting the first evaluation score and the second evaluation score into an emotional dictionary for a previously generated care service evaluation item, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; And instructions for inputting the first word set, the second word set, and the first service usage review into a generative AI model, and performing an operation of generating a second service usage review as a result of the input, wherein the user information includes basic information of the guardian and basic information of the patient, the care information includes disease information of the patient, and the first evaluation score may be a value greater than or equal to the second evaluation score.

[0017] In one embodiment, the operation of obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score includes: calculating a first weighted score for the first evaluation score and a second weighted score for the second evaluation score; and obtaining the first word set corresponding to the first weighted score and the second word set corresponding to the second weighted score, wherein the first weighted score is a value obtained by subtracting an average of the first evaluation score and the second evaluation score from the first evaluation score, and the second weighted score is a value obtained by subtracting the average from the second evaluation score, and the first word set may include as many positive words as the number corresponding to the first weighted score, and the second word set may include as many negative words as the number corresponding to the absolute value of the second weighted score.

[0018] In one embodiment, the generating operation includes: receiving a request for modification of the generated second service usage review from the user terminal; in response to the received modification request, correcting the first evaluation score to obtain a first modified evaluation score and correcting the second evaluation score to obtain a second modified evaluation score; inputting the first modified evaluation score and the second modified evaluation score into the emotional dictionary, and obtaining a third word set corresponding to the first modified evaluation score and a fourth word set corresponding to the second modified evaluation score; and inputting the third word set, the fourth word set, and the first service usage review into the generative AI model, and regenerating the third service usage review as a result of the input, wherein the modification request may be at least one of a first option for increasing the first evaluation score and the second evaluation score by a first set value and a second option for decreasing the first evaluation score and the second evaluation score by the first set value.

[0019] In one embodiment, the generating operation includes: receiving a request for modification of the generated second service usage review from the user terminal; obtaining a first corrected evaluation score by correcting the first evaluation score in response to the received modification request; entering the first corrected evaluation score into the emotional dictionary and obtaining a third word set corresponding to the first corrected evaluation score; and entering the third word set, the second word set, and the first service usage review into the generative AI model and regenerating the third service usage review as a result of the input, wherein the modification request may be at least one of a first option for increasing the first evaluation score by a first set value and a second option for decreasing the first evaluation score by the first set value.

[0020] According to an embodiment of the present disclosure for solving the above technical problem, a computer program is stored in a computer-readable recording medium that is coupled to a computing device and executes the steps of: obtaining a first service usage review having a similarity level higher than a reference value by using user information and nursing information of a nursing service used by the user; obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the nursing service from a user terminal; inputting the first evaluation score and the second evaluation score into an emotional dictionary for previously generated nursing service evaluation items, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and inputting the first word set, the second word set, and the first service usage review into a generative AI model, and generating a second service usage review as a result of the input, wherein the user information includes basic information of a guardian and basic information of a patient, the nursing information includes disease information of the patient, and the first evaluation score may be a value greater than or equal to the second evaluation score.

[0021] FIG. 1 is a system configuration diagram for explaining the configuration and operation of a service usage review generation system according to one embodiment of the present disclosure.

[0022] FIG. 2 is a flowchart illustrating a method for generating a service usage review according to another embodiment of the present disclosure.

[0023] FIG. 3 is a diagram illustrating user information, care information, and a first service usage review referenced by some embodiments of the present disclosure.

[0024] FIG. 4 is a diagram illustrating evaluation items and evaluation scores for nursing services referenced by some embodiments of the present disclosure.

[0025] FIG. 5 is a diagram illustrating an emotional dictionary for evaluation items of nursing services referenced by some embodiments of the present disclosure.

[0026] FIG. 6 is a detailed flowchart for explaining a method for generating a service usage review according to another embodiment of the present disclosure, described with reference to FIG. 2.

[0027] FIG. 7 is a diagram illustrating a service usage review generated by another embodiment of the present disclosure.

[0028] FIG. 8 is a detailed flowchart for explaining a method for generating a service usage review according to another embodiment of the present disclosure, described with reference to FIG. 2.

[0029] FIG. 9 is an exemplary diagram illustrating the operation of a service usage review generation method according to another embodiment of the present disclosure.

[0030] FIG. 10 is a detailed flowchart for explaining a method for generating a service usage review according to another embodiment of the present disclosure, described with reference to FIG. 2.

[0031] FIG. 11 is an exemplary diagram illustrating the operation of a service usage review generation method according to another embodiment of the present disclosure.

[0032] FIG. 12 is a hardware configuration diagram of a computing device described in some embodiments of the present disclosure.

[0033] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the attached drawings. The advantages and features of the present invention, and methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the attached drawings. However, the technical spirit of the present invention is not limited to the following embodiments and may be implemented in various different forms. The following embodiments are provided only to complete the technical spirit of the present invention and to fully inform those skilled in the art of the present invention of the scope of the present invention, and the technical spirit of the present invention is defined only by the scope of the claims.

[0034] In describing the present disclosure, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description will be omitted.

[0035] Unless otherwise defined, the terms (including technical and scientific terms) used in the following examples may be used with meanings commonly understood by those of ordinary skill in the art to which this disclosure pertains; however, this may vary depending on the intentions of engineers working in the relevant field, precedents, the emergence of new technologies, etc. The terminology used in this disclosure is for the purpose of describing the embodiments and is not intended to limit the scope of this disclosure.

[0036] In the following examples, singular expressions include plural concepts unless the context clearly specifies that they are singular. Furthermore, plural expressions include singular concepts unless the context clearly specifies that they are plural.

[0037] In addition, terms such as first, second, A, B, (a), (b), etc. used in the following embodiments are only used to distinguish certain components from other components, and the nature, order, or sequence of the components are not limited by the terms.

[0038] Various embodiments of the present disclosure will be described below with reference to the attached drawings.

[0039] Hereinafter, with reference to FIG. 1, the configuration and operation of a service usage review generation system according to one embodiment of the present disclosure will be described. FIG. 1 is a system configuration diagram for explaining the configuration and operation of a service usage review generation system according to one embodiment of the present disclosure.

[0040] Referring to FIG. 1, the service review generation system may be configured to include a caregiver matching platform (10) and multiple user terminals (20). However, the scope of the present disclosure is not limited thereto. In some cases, the service review generation system may be configured to further include modules / devices / systems not illustrated in FIG. 1. Alternatively, the service review generation system may be configured to exclude at least some of the components (10 and 20) illustrated in FIG. 1.

[0041] The user terminal (20) may include multiple user terminals. Although FIG. 1 only illustrates a first user terminal (21) and a second user terminal (22), the scope of the present disclosure is not limited thereto, and the user terminal (20) may include three or more user terminals.

[0042] The caregiver matching platform (10) may be configured to include a service server (11), a generative AI model (12), and a database (13). However, the scope of the present disclosure is not limited thereto. In some cases, the caregiver matching platform (10) may be configured to further include modules / devices / systems not illustrated in FIG. 1. Alternatively, the caregiver matching platform may be configured to exclude at least some of the components (11 to 13) illustrated in FIG. 1.

[0043] The user terminal (20) may be the terminal of a user who has recruited a caregiver through the caregiver matching platform (10). The user may be a patient who has received care services or a guardian of the patient. The user may write a service review of the care services provided by the caregiver recruited through the caregiver matching platform (10). The user terminal (20) may transmit the written service review to the caregiver matching platform (10).

[0044] The caregiver matching platform (10) can store service usage reviews transmitted from user terminals (20) in a database (13). The database (13) can store a sentiment dictionary for previously created evaluation items of care services. The sentiment dictionary may include positive and negative words for various evaluation items of care services. The sentiment dictionary will be described in detail with reference to FIG. 5.

[0045] The service server (11) can receive user information and care information regarding the care service used by the user from the user terminal (20). The user information may include basic information about the patient (e.g., age, gender, etc.) and basic information about the patient's guardian (e.g., age, gender). The care information may include disease information about the patient.

[0046] The service server (11) can use the user information and the care information to obtain a first service review having a similarity level higher than a standard value among the service reviews written by the user terminal (20).

[0047] The above user information, the above care information, and the above first service usage review are described in detail with reference to FIG. 3.

[0048] The service server (11) can obtain evaluation scores for various evaluation items for the nursing service provided to the user from the user terminal (20). The service server (11) can input the evaluation scores for the evaluation items into the emotional dictionary and obtain a word set corresponding to each evaluation score. This will be described in detail with reference to FIG. 4.

[0049] The service server (11) inputs a word set corresponding to each of the above evaluation scores and the first service review into a generative AI model (12), and can generate a new service review as a result of the input. The generative AI model (12) is a model based on a large-scale language model (LLM), and may be a model based on a Transformer model, which is a neural network architecture. The generative AI model (12) may be a model that exhibits superior performance in natural language processing. Since the generative AI model (12) is something that a person of ordinary skill in the art to which the invention of the present disclosure belongs would already be familiar with, a detailed description thereof will be omitted.

[0050] The generative AI model (12) can generate a new service review by combining the input word set with the first service review. This will be described in detail with reference to FIGS. 6 and 7.

[0051] The service server (11) may receive a request to modify a service review generated from a user terminal (20). In this case, in response to the modification request, the service server (11) requests the generative AI model (12) to regenerate a new service review, and the generative AI model (12) may regenerate the new service review. This will be described in detail with reference to FIGS. 8 to 11.

[0052] For ease of understanding, the following description assumes that all steps / operations of the methods described below are performed on the aforementioned service server (11). Therefore, if the subject of a specific step / operation is omitted, it can be understood that it is performed on the service server (11). However, in an actual environment, some steps / operations of the methods described below may be performed on other computing devices.

[0053] Hereinafter, a method for generating a service review according to one embodiment of the present disclosure will be described with reference to FIG. 2. FIG. 2 is a flowchart illustrating a method for generating a service review according to another embodiment of the present disclosure.

[0054] Referring to FIG. 2, the service server (11) can obtain a first service usage review having a similarity level higher than a reference value by using user information and care information of the care service used by the user (S100). The user information may include basic information of the patient and basic information of the patient's guardian. The care information may include disease information of the patient. Hereinafter, user information, care information, and a first service usage review referenced by some embodiments of the present disclosure will be described with reference to FIG. 3. FIG. 3 is a diagram illustrating user information, care information, and a first service usage review referenced by some embodiments of the present disclosure.

[0055] Referring to Fig. 3, user information and care information (30) and a first service usage review (31) are illustrated. The user information and care information (30) and the first service usage review (31) may be stored in a database (13), and the user information and care information (30) may be preprocessed information based on basic information of the patient and guardian entered by the user.

[0056] For example, user information (30) may include information that the guardian is a woman in her 30s, the patient is a man in his 60s, and the relationship between the guardian and patient is that of father and daughter. Care information (30) may include information about the disease the patient is suffering from, such as cerebral hemorrhage.

[0057] The service server (11) can obtain first service usage reviews that have a similarity level higher than a threshold with user information and care information (30). The threshold may be set differently depending on the situation.

[0058] The service server (11) can obtain a service review written by a patient or guardian who has the same information as the user information and care information (30) from the database (13). That is, the service server (11) can compare the user information and care information (30) with second user information and second care information of another user who is different from the user, and obtain a service review of a user who has second user information and second care information that are higher than a reference value as a result of the comparison. For example, if the second user information is that the guardian is in his 30s, the patient is a male in his 60s, the relationship between the guardian and the patient is that of a father and a child, and the second care information is cerebral hemorrhage, the service server (11) can obtain a service review of the user who has the second user information and second care information.

[0059] At this time, there may be multiple service reviews acquired, and the service server (11) may randomly select one of the acquired service reviews. For example, the service server (11) may select the service review that receives the most likes or recommendations from among the acquired service reviews. However, the scope of the present disclosure is not limited to this, and the service server (11) may select one of the acquired service reviews using various methods.

[0060] For convenience of explanation in this disclosure, it is assumed that the service server (11) selected the first service usage review (31) from among the acquired service usage reviews, as shown in FIG. 3.

[0061] Again, this is explained with reference to Fig. 2.

[0062] When the service server (11) obtains a first service usage review having a similarity level higher than a threshold, the service server (11) can obtain a first evaluation score for the first evaluation item and a second evaluation score for the second evaluation item for the nursing service used by the user from the user terminal (20) (S200). In this case, the first evaluation score may be greater than or equal to the second evaluation score. It should be noted that this is inevitably limited to allow for comparison based on the difference in magnitude between the first and second evaluation scores in the embodiments described later.

[0063] Hereinafter, with reference to FIG. 4, evaluation items and evaluation scores for nursing services referenced by some embodiments of the present disclosure are described. FIG. 4 is a diagram illustrating evaluation items and evaluation scores for nursing services referenced by some embodiments of the present disclosure.

[0064] Referring to FIG. 4, a table (40) showing evaluation items and evaluation scores input by a user is illustrated. The evaluation items may include a first evaluation item (41) regarding the caregiver's friendliness, a second evaluation item (42) regarding the caregiver's sense of responsibility, a third evaluation item (43) regarding the caregiver's cleanliness, a fourth evaluation item (44) regarding the caregiver's communication skills, and a fifth evaluation item (45) regarding the caregiver's skill level. In the present disclosure, for the convenience of explanation, it is assumed that the evaluation scores for each evaluation item are entered as natural numbers from 0 to 5.

[0065] For example, a user may input 4 points as the first evaluation score for the first evaluation item (41), 4 points as the second evaluation score for the second evaluation item (42), 2 points as the third evaluation score for the third evaluation item (43), 3 points as the fourth evaluation score for the fourth evaluation item (44), and 2 points as the fifth evaluation score for the fifth evaluation item (45). In the embodiment described below, the explanation will continue on the assumption that the service server (11) obtains evaluation scores for each evaluation item from the user terminal (20) as shown in Table (40).

[0066] Again, this is explained with reference to Fig. 2.

[0067] When the service server (11) obtains an evaluation score for each evaluation item for the nursing service, the service server (11) inputs the first evaluation score and the second evaluation score into an emotional dictionary for the previously generated evaluation items of the nursing service, and obtains a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score (S300). Hereinafter, an emotional dictionary for evaluation items of the nursing service, which is referenced by some embodiments of the present disclosure, will be described with reference to FIG. 5. FIG. 5 is a diagram illustrating an emotional dictionary for evaluation items of the nursing service, which is referenced by some embodiments of the present disclosure.

[0068] Referring to Fig. 5, an emotional dictionary (50) is illustrated. The emotional dictionary (50) may include a first evaluation item (51) regarding the kindness of the caregiver, a second evaluation item (52) regarding the responsibility of the caregiver, a third evaluation item (53) regarding the cleanliness of the caregiver, a fourth evaluation item (54) regarding the communication skills of the caregiver, and a fifth evaluation item (55) regarding the skill of the caregiver, and positive and negative words for each evaluation item (51 to 55).

[0069] For example, positive words for the first evaluation item (51) may include words such as ‘trust’ and ‘take good care of’, and negative words for the first evaluation item (51) may include words such as ‘rude’ and ‘annoying’.

[0070] For example, positive words for the second evaluation item (52) may include words such as 'responsibility' and 'meticulousness', and negative words for the second evaluation item (52) may include words such as 'throw away' and 'irresponsibility'.

[0071] For example, positive words for the third evaluation item (53) may include words such as 'clean' and 'neatly', and negative words for the third evaluation item (53) may include words such as 'dirty' and 'without going'.

[0072] For example, positive words for the fourth evaluation item (54) may include words such as ‘active’, ‘comfortable’, and ‘safe’, and negative words for the fourth evaluation item (54) may include words such as ‘no words’, and ‘as one pleases’.

[0073] For example, positive words for the fifth evaluation item (55) may include words such as ‘well done’ and ‘best’, and negative words for the fifth evaluation item (55) may include words such as ‘don’t know’ and ‘clumsy’.

[0074] However, the scope of the present disclosure is not limited thereto, and various positive and negative words may be included for each evaluation item.

[0075] Below, step S300 is described in more detail with reference to FIG. 6.

[0076] Referring to FIG. 6, the service server (11) can calculate a first weighted score for the first evaluation score and a second weighted score for the second evaluation score (S310). The first weighted score may be a value obtained by subtracting the average of the first and second evaluation scores from the first evaluation score, and the second weighted score may be a value obtained by subtracting the average of the first and second evaluation scores from the second evaluation score.

[0077] For example, the first evaluation score may be 4 points, and as explained above, the second evaluation score may be 2 points because it is less than or equal to the first evaluation score. In this case, the first weighted score may be 1 point, which is the first evaluation score of 4 points minus 3 points, which is the average of the first and second evaluation scores, and the second weighted score may be -1 point, which is the second evaluation score of 2 points minus 3 points, which is the average of the first and second evaluation scores.

[0078] Thereafter, the service server (11) can obtain a first word set corresponding to the first weighted score and a second word set corresponding to the second weighted score (S320). The first word set may include as many positive words as the number corresponding to the first weighted score, and the second word set may include as many negative words as the number corresponding to the second weighted score. In this case, the second weighted score may be a negative number because the first evaluation score is greater than or equal to the second evaluation score. Therefore, the number corresponding to the second weighted score means the number corresponding to the absolute value of the second weighted score.

[0079] In the above example, if the first weighted score is 1 point and the second weighted score is -1 point, the number corresponding to the first weighted score is 1, and the number corresponding to the second weighted score is 1. Therefore, in this case, the first word set corresponding to the first weighted score may include one positive word for the first evaluation item, and the second word set corresponding to the second weighted score may include one negative word for the second evaluation item.

[0080] Meanwhile, the first weighted score and the second weighted score may be decimals rather than natural numbers. For example, if the first evaluation score is 4 and the second evaluation score is 1, the first weighted score is 1.5 and the second weighted score is -1.5. In this case, the number corresponding to the first weighted score may be 1, which is the number obtained by rounding down the first weighted score. On the other hand, the number corresponding to the second weighted score may be 1, which is the number obtained by rounding down 1.5, which is the number corresponding to the absolute value of the second weighted score. In this case, the first word set corresponding to the first weighted score may include one positive word for the first evaluation item, and the second word set corresponding to the second weighted score may include one negative word for the second evaluation item. However, the scope of the present disclosure is not limited thereto, and in some cases, the service server (11) may perform different operations, such as a rounding operation, on the number corresponding to the first weighted score and the number corresponding to the second weighted score.

[0081] Again, this is explained with reference to Fig. 2.

[0082] When the service server (11) obtains the first word set and the second word set (S300), the service server (11) inputs the first word set, the second word set, and the first service review into the generative AI model (12), and can generate a second service review, which is a new service review, as a result of the input (S400). Hereinafter, a service review generated by one embodiment of the present disclosure will be described with reference to FIG. 7. FIG. 7 is a diagram illustrating a service review generated by another embodiment of the present disclosure.

[0083] Referring to FIG. 7, as in FIG. 4, it is assumed that the service server (11) obtains 4 points as the first evaluation score for the first evaluation item (41), 4 points as the second evaluation score for the second evaluation item (42), 2 points as the third evaluation score for the third evaluation item (43), 3 points as the fourth evaluation score for the fourth evaluation item (44), and 2 points as the fifth evaluation score for the fifth evaluation item (45) from the user terminal (20).

[0084] The service server (11) can input an evaluation score for each evaluation item into the emotional dictionary illustrated in FIG. 5. The service server (11) can obtain 'well-taken care of' as a first word set corresponding to the first evaluation score for the first evaluation item (41). The service server (11) can obtain 'meticulously' as a second word set corresponding to the second evaluation score for the second evaluation item (42). The service server (11) can obtain 'not changing (=not changing)' as a third word set corresponding to the third evaluation score for the third evaluation item (43). The service server (11) may not obtain any words as a fourth word set corresponding to the fourth evaluation score for the fourth evaluation item (44). The service server (11) can obtain 'clumsily' as a fifth word set corresponding to the evaluation score for the fifth evaluation item (45).

[0085] Thereafter, the service server (11) inputs the first word set to the fifth word set and the first service review (31) obtained as in FIG. 3 into the generative AI model (12), and can generate a second service review (70) as a result of the input. That is, the service server (11) automatically writes a prompt saying, 'Please write a review about the nursing service using the first word set to the fifth word set and the first service review (31),' and inputs the written prompt together with the first word set to the fifth word set and the first service review (31) into the generative AI model (12), thereby generating the second service review (70) illustrated in FIG. 7.

[0086] According to some of the above embodiments, a service review for a nursing service can be automatically generated by inputting a service review written by another user (patient or guardian) and an evaluation score for each evaluation item of the nursing service entered by that user into a generative AI model (12). Therefore, according to some of the above embodiments, there is an advantage in that patients or guardians can easily and conveniently input a service review for a nursing service.

[0087] Hereinafter, with reference to FIG. 8, a method for generating a service review according to another embodiment of the present disclosure will be described. FIG. 8 is a detailed flowchart illustrating a method for generating a service review according to another embodiment of the present disclosure, as described with reference to FIG. 2.

[0088] Referring to FIG. 8, the service server (11) may receive a request for modification of a second service usage review generated from a user terminal (20) (S410). At this time, the modification request may be at least one of a first option for increasing a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item received from the user terminal (20) by a first set value, and a second option for decreasing the first evaluation score and the second evaluation score by the first set value. For example, the first set value may be 1 point, which means the smallest unit score value that can change the evaluation score for each evaluation item. That is, the first option may be to increase the first evaluation score and the second evaluation score by 1 point, and the second option may be to decrease the first evaluation score and the second evaluation score by 1 point. That is, the user may input an option for increasing or decreasing the evaluation score for all evaluation items of the nursing service through the modification request.

[0089] Thereafter, the service server (11) can, in response to the above modification request, correct the first evaluation score for the first evaluation item received from the user terminal (20) to obtain a first corrected evaluation score, and correct the second evaluation score for the second evaluation item to obtain a second corrected evaluation score (S411). That is, the service server (11) can increase or decrease the first evaluation score and the second evaluation score by a first set value to obtain a first corrected evaluation score for the first evaluation score and a second corrected evaluation score for the second evaluation score.

[0090] Meanwhile, in one embodiment, there may be a case where the first correction evaluation score exceeds the maximum evaluation score for the first evaluation item. That is, there may be a case where the service server (11) receives the first option from the user terminal (20) when the first evaluation score is 5 points. In this case, the service server (11) corrects the first evaluation score to obtain 6 points as the first correction evaluation score.

[0091] However, as previously explained, the first evaluation score for the first evaluation item can only be entered as a natural number between the minimum evaluation score of 0 and the maximum evaluation score of 5. Therefore, in this case, the service server (11) can set the first correction evaluation score to the maximum evaluation score. That is, the service server (11) can set the first correction evaluation score to the maximum evaluation score of 5.

[0092] On the other hand, in one embodiment, there may be a case where the second correction evaluation score is less than the minimum evaluation score for the second evaluation item. That is, there may be a case where the service server (11) receives the second option from the user terminal (20) when the second evaluation score is 0. In this case, the service server (11) corrects the second evaluation score to obtain -1 point as the second correction evaluation score.

[0093] However, as previously explained, the second evaluation score for the second evaluation item can only be entered as a natural number between the minimum evaluation score of 0 and the maximum evaluation score of 5. Therefore, in this case, the service server (11) can set the second correction evaluation score to the minimum evaluation score. That is, the service server (11) can set the second correction evaluation score to the minimum evaluation score of 0.

[0094] According to the above two embodiments, systemic errors can be prevented in advance by preventing situations where the evaluation score for each evaluation item exceeds the maximum evaluation score or falls below the minimum evaluation score. Therefore, the above two embodiments have the advantage of enhancing the reliability of the caregiver matching platform (10) and providing stable services.

[0095] Again, this is explained with reference to Fig. 8.

[0096] When the service server (11) obtains the first correction evaluation score and the second correction evaluation score (S411), the service server (11) inputs the first correction evaluation score and the second correction evaluation score into the emotional dictionary illustrated in FIG. 5, and can obtain a third word set corresponding to the first correction evaluation score and a fourth word set corresponding to the second correction evaluation score (S412). The method for obtaining the third word set and the fourth word set can be implemented as the method described with reference to FIGS. 6 and 7.

[0097] Thereafter, the service server (11) inputs the third word set, the fourth word set, and the first service review obtained through step S100 of FIG. 2 into the generative AI model (12), and as a result of the input, a new service review, a third service review, can be generated again (S413). The method for generating the third service review can be implemented as described with reference to FIG. 7.

[0098] Hereinafter, with reference to FIG. 9, the operation of a service review generation method according to one embodiment of the present disclosure, described with reference to FIG. 8, will be described in more detail. FIG. 9 is an exemplary diagram illustrating the operation of a service review generation method according to another embodiment of the present disclosure.

[0099] Referring to FIG. 9, it is assumed that the service server (11) obtained 4 points as a first evaluation score (41) for a first evaluation item, 4 points as a second evaluation score (42) for a second evaluation item, 2 points as a third evaluation score (43) for a third evaluation item, 3 points as a fourth evaluation score (44) for a fourth evaluation item, and 2 points as a fifth evaluation score (45) for a fifth evaluation item from the user terminal (20). In addition, it is assumed that the service server (11) inputs a word set corresponding to the evaluation score for each evaluation item and a first service review (31) into a generative AI model (12), and generates a second service review (70) as a result of the input.

[0100] A user can input a first option (80) that increases the evaluation scores for all evaluation items by a first set value (=1 point) through a user terminal (20). The service server (11) can receive the first option (80) as a request for modification of a second service usage review (70) from the user terminal (20). In this case, the service server (11) can correct the first evaluation score (41) to obtain 5 points as a first corrected evaluation score (81), correct the second evaluation score (42) to obtain 5 points as a second corrected evaluation score (82), correct the third evaluation score (43) to obtain 3 points as a third corrected evaluation score (83), correct the fourth evaluation score (44) to obtain 4 points as a fourth corrected evaluation score, and correct the fifth evaluation score (45) to obtain 3 points as a fifth corrected evaluation score.

[0101] The service server (11) can input the correction evaluation score for each evaluation item into the emotional dictionary shown in FIG. 5. The service server (11) can obtain 'take good care of' and 'trust' as a first word set corresponding to the first correction evaluation score (81). The service server (11) can obtain 'meticulously' and 'sense of responsibility' as a second word set corresponding to the second correction evaluation score (82). The service server (11) may not obtain any words as a third word set corresponding to the third correction evaluation score (83). The service server (11) may obtain 'comfortably' as a fourth word set corresponding to the fourth correction evaluation score (84). The service server (11) may not obtain any words as a fifth word set corresponding to the fifth correction evaluation score (85).

[0102] Thereafter, the service server (11) inputs the first word set to the fifth word set and the first service review (31) obtained as in FIG. 3 into the generative AI model (12), and can generate a third service review (86) again as a result of the input. That is, the service server (11) automatically writes a prompt saying, 'Please write a review about the nursing service using the first word set to the fifth word set and the first service review (31),' and inputs the written prompt together with the first word set to the fifth word set and the first service review (31) into the generative AI model (12), thereby generating the third service review (86) illustrated in FIG. 9.

[0103] According to the above-described embodiments, if a user is dissatisfied with a service review automatically generated by the caregiver matching platform (10), the user can easily and conveniently edit the service review by clicking the first option (80) or the second option (not shown), as illustrated in FIG. 9. Therefore, the above-described embodiments have the advantage of allowing patients or guardians to easily and conveniently enter a service review regarding caregiving services.

[0104] Hereinafter, with reference to FIG. 10, a method for generating a service review according to another embodiment of the present disclosure will be described. FIG. 10 is a detailed flowchart illustrating a method for generating a service review according to another embodiment of the present disclosure, as described with reference to FIG. 2.

[0105] Referring to FIG. 10, the service server (11) may receive a request for modification of a second service usage review generated from a user terminal (20) (S420). At this time, the modification request may be at least one of a first option for increasing a first evaluation score for a first evaluation item received from the user terminal (20) by a first set value and a second option for decreasing the first evaluation score by the first set value. For example, the first set value may be 1 point, which means the smallest unit score value that can change the evaluation score for each evaluation item. That is, the first option may increase the first evaluation score by 1 point, and the second option may decrease the first evaluation score by 1 point. That is, the user may input an option for increasing or decreasing the evaluation score for each evaluation item of the nursing service through the modification request.

[0106] Thereafter, in response to the above modification request, the service server (11) can correct the first evaluation score for the first evaluation item received from the user terminal (20) to obtain a first corrected evaluation score (S421). That is, the service server (11) can obtain a first corrected evaluation score for the first evaluation score by increasing or decreasing the first evaluation score by a first set value.

[0107] Meanwhile, in one embodiment, there may be a case where the first correction evaluation score exceeds the maximum evaluation score for the first evaluation item. That is, there may be a case where the service server (11) receives the first option from the user terminal (20) when the first evaluation score is 5 points. In this case, the service server (11) corrects the first evaluation score to obtain 6 points as the first correction evaluation score.

[0108] However, as previously explained, the first evaluation score for the first evaluation item can only be entered as a natural number between the minimum evaluation score of 0 and the maximum evaluation score of 5. Therefore, in this case, the service server (11) can set the first correction evaluation score to the maximum evaluation score. That is, the service server (11) can set the first correction evaluation score to the maximum evaluation score of 5.

[0109] On the other hand, in one embodiment, there may be a case where the first correction evaluation score is less than the minimum evaluation score for the first evaluation item. That is, there may be a case where the service server (11) receives the second option from the user terminal (20) when the first evaluation score is 0. In this case, the service server (11) corrects the first evaluation score to obtain -1 point as the first correction evaluation score.

[0110] However, as previously explained, the first evaluation score for the first evaluation item can only be entered as a natural number between the minimum evaluation score of 0 and the maximum evaluation score of 5. Therefore, in this case, the service server (11) can set the first correction evaluation score to the minimum evaluation score. In other words, the service server (11) can set the first correction evaluation score to the minimum evaluation score of 0.

[0111] According to the above two embodiments, systemic errors can be prevented in advance by preventing situations where the evaluation score for each evaluation item exceeds the maximum evaluation score or falls below the minimum evaluation score. Therefore, the above two embodiments have the advantage of enhancing the reliability of the caregiver matching platform (10) and providing stable services.

[0112] Again, this is explained with reference to Fig. 10.

[0113] When the service server (11) obtains the first correction evaluation score (S421), the service server (11) can input the first correction evaluation score into the emotional dictionary illustrated in FIG. 5 and obtain a third word set corresponding to the first correction evaluation score (S422). The method for obtaining the third word set can be implemented as described with reference to FIGS. 6 and 7.

[0114] Thereafter, the service server (11) inputs the third word set, the second word set corresponding to the second evaluation score described with reference to FIGS. 2 and 6, and the first service review obtained through step S100 of FIG. 2 into the generative AI model (12), and can re-generate a new service review, a third service review, as a result of the input (S423). The method for generating the third service review can be implemented in the same manner as the method described with reference to FIG. 7.

[0115] Hereinafter, with reference to FIG. 11, the operation of a service review generation method according to one embodiment of the present disclosure, described with reference to FIG. 10, will be described in more detail. FIG. 11 is an exemplary diagram illustrating the operation of a service review generation method according to another embodiment of the present disclosure.

[0116] Referring to FIG. 11, it is assumed that the service server (11) obtains 4 points as a first evaluation score (41) for a first evaluation item, 4 points as a second evaluation score (42) for a second evaluation item, 2 points as a third evaluation score (43) for a third evaluation item, 3 points as a fourth evaluation score (44) for a fourth evaluation item, and 2 points as a fifth evaluation score (45) for a fifth evaluation item from the user terminal (20). In addition, it is assumed that the service server (11) inputs a word set corresponding to the evaluation score for each evaluation item and a first service review (31) into a generative AI model (12), and generates a second service review (70) as a result of the input.

[0117] A user may input a second option (110) that reduces the evaluation score (42) for the second evaluation item by a first set value (=1 point) through the user terminal (20). The service server (11) may receive the second option (110) as a request for modification of the second service usage review (70) from the user terminal (20). In this case, the service server (11) may correct the second evaluation score (42) to obtain 3 points as the second corrected evaluation score (111).

[0118] The service server (11) can input the second correction evaluation score (111) into the emotional dictionary illustrated in Fig. 5. The service server (11) may not obtain a word as a third word set corresponding to the first correction evaluation score.

[0119] Thereafter, the service server (11) inputs the previously acquired word set, the third word set corresponding to the first correction evaluation score, and the first service review (31) acquired as shown in FIG. 3, into the generative AI model (12), and can generate a second service review (112) as a result of the input. That is, the service server (11) automatically creates a prompt to write a review about a nursing service using the previously acquired word set, the third word set corresponding to the first correction evaluation score, and the first service review (31) acquired as shown in FIG. 3, and inputs the created prompt together with the previously acquired word set, the third word set corresponding to the first correction evaluation score, and the first service review (31) into the generative AI model (12), thereby generating the third service review (112) illustrated in FIG. 11.

[0120] According to some of the above embodiments, if a user is dissatisfied with a service review automatically generated by the caregiver matching platform (10), the user can easily and conveniently edit the service review by clicking the first option (not shown) or the second option (110), as illustrated in FIG. 9. Therefore, according to some of the above embodiments, there is an advantage in that patients or guardians can easily and conveniently enter a service review for a caregiver service.

[0121] FIG. 12 is a hardware configuration diagram of a computing device according to some embodiments of the present disclosure. The computing device (1000) of FIG. 12 may include one or more processors (1100), a system bus (1600), a communication interface (1200), a memory (1400) for loading a computer program (1500) executed by the processor (1100), and a storage (1300) for storing the computer program (1500).

[0122] The computing system (1000) of FIG. 12 may present a hardware structure of one or more computing systems constituting the service server (11) described with reference to FIG. 1, for example.

[0123] The processor (1100) controls the overall operation of each component of the computing system (1000). The processor (1100) can perform operations for at least one application or program for executing methods / operations according to various embodiments of the present disclosure. The memory (1400) stores various data, commands, and / or information. The memory (1400) can load one or more computer programs (1500) from the storage (1300) to execute methods / operations according to various embodiments of the present disclosure. The storage (1300) can non-temporarily store one or more computer programs (1500).

[0124] The computer program (1500) may include one or more instructions implementing methods / operations according to various embodiments of the present disclosure. When the computer program (1500) is loaded into the memory (1400), the processor (1100) may execute the one or more instructions to perform the methods / operations according to various embodiments of the present disclosure.

[0125] In one embodiment, the computer program (1500) includes instructions for performing the following operations: obtaining a first service usage review having a similarity level higher than a reference value by using user information and care information of a care service used by the user; obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the care service from a user terminal; inputting the first evaluation score and the second evaluation score into an emotion dictionary for previously generated care service evaluation items, obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and inputting the first word set, the second word set, and the first service usage review into a generative AI model (12) and generating a second service usage review as a result of the input, wherein the user information includes basic information of a guardian and basic information of a patient, the care information includes disease information of the patient, and the first evaluation score may be a value greater than or equal to the second evaluation score.

[0126] Various embodiments of the present disclosure and effects according to the embodiments have been described with reference to FIGS. 1 through 12. The effects according to the technical concept of the present disclosure are not limited to the effects described above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0127] Furthermore, even though the above embodiments have described multiple components as being combined or operating in combination, the technical concept of the present disclosure is not necessarily limited to these embodiments. That is, within the scope of the technical concept of the present disclosure, all of the components may be selectively combined and operated one or more times.

[0128] The technical concepts of the present disclosure described so far can be implemented as computer-readable code on a computer-readable medium. A computer program recorded on a computer-readable recording medium can be transmitted to another computing device via a network such as the Internet, installed on said other computing device, and thus used on said other computing device.

Claims

1. In a method performed by a computing device, A step of obtaining a first service usage review having a similarity level higher than a standard value by using user information and nursing information of a nursing service used by the user; A step of obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the nursing service from a user terminal; A step of inputting the first evaluation score and the second evaluation score into an emotional dictionary for the previously generated nursing service evaluation items, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and A step of inputting the first word set, the second word set, and the first service usage review into a generative AI model, and generating a second service usage review as a result of the input, The above user information is, Includes basic information of the guardian and basic information of the patient, The above care information is, Contains information on the above patient's disease, The above first evaluation score is, A value greater than or equal to the second evaluation score above, How to create a service review.

2. In paragraph 1, The step of obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score is as follows: A step of calculating a first weighted score for the first evaluation score and a second weighted score for the second evaluation score; and A step of obtaining the first word set corresponding to the first weighted score and the second word set corresponding to the second weighted score, The above first weighted score is, The value obtained by subtracting the average of the first evaluation score and the second evaluation score from the first evaluation score, The above second weighted score is, The value obtained by subtracting the above average from the above second evaluation score, The above first set of words is, Contains as many positive words as the number corresponding to the first weighted score above, The second set of words above is, Contains as many negative words as the number corresponding to the absolute value of the second weighted score, How to create a service review.

3. In paragraph 1, The above generating steps are: A step of receiving a request for modification of the generated second service usage review from the user terminal; In response to the received modification request, a step of correcting the first evaluation score to obtain a first corrected evaluation score, and correcting the second evaluation score to obtain a second corrected evaluation score; A step of inputting the first correction evaluation score and the second correction evaluation score into the emotional dictionary, and obtaining a third word set corresponding to the first correction evaluation score and a fourth word set corresponding to the second correction evaluation score; and A step of inputting the third word set, the fourth word set, and the first service usage review into the generative AI model, and regenerating the third service usage review as a result of the input, The above request for modification is, At least one of a first option for increasing the first evaluation score and the second evaluation score by a first set value and a second option for decreasing the first evaluation score and the second evaluation score by the first set value, How to create a service review.

4. In paragraph 3, The step of obtaining a first corrected evaluation score by correcting the first evaluation score and obtaining a second corrected evaluation score by correcting the second evaluation score is as follows: Including a step of setting the first correction evaluation score to the maximum evaluation score when the first correction evaluation score exceeds the maximum evaluation score for the first evaluation item. How to create a service review.

5. In paragraph 3, The step of obtaining a first corrected evaluation score by correcting the first evaluation score and obtaining a second corrected evaluation score by correcting the second evaluation score is as follows: Including a step of setting the second correction evaluation score to the minimum evaluation score when the second correction evaluation score is less than the minimum evaluation score for the second evaluation item. How to create a service review.

6. In paragraph 1, The above generating steps are: A step of receiving a request for modification of the generated second service usage review from the user terminal; In response to the received modification request, a step of correcting the first evaluation score to obtain a first corrected evaluation score; A step of inputting the first correction evaluation score into the emotional dictionary and obtaining a third word set corresponding to the first correction evaluation score; and A step of inputting the third word set, the second word set, and the first service usage review into the generative AI model, and regenerating the third service usage review as a result of the input, The above request for modification is, At least one of a first option for increasing the first evaluation score by a first set value and a second option for decreasing the first evaluation score by the first set value, How to create a service review.

7. In paragraph 6, The step of obtaining a first corrected evaluation score by correcting the first evaluation score is as follows: Including a step of setting the first correction evaluation score to the maximum evaluation score when the first correction evaluation score exceeds the maximum evaluation score for the first evaluation item. How to create a service review.

8. In paragraph 6, The step of obtaining a first corrected evaluation score by correcting the first evaluation score is as follows: Including a step of setting the first correction evaluation score to the minimum evaluation score when the first correction evaluation score is less than the minimum evaluation score for the first evaluation item. How to create a service review.

9. Communication interface; Memory into which computer programs are loaded; and Including one or more processors on which the above computer program is executed, The above computer program, An action of obtaining a first service usage review having a similarity level higher than a standard value by using user information and nursing information of a nursing service used by the user; An operation of obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the above-mentioned nursing service from a user terminal; An operation of inputting the first evaluation score and the second evaluation score into an emotional dictionary for the previously generated nursing service evaluation items, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and Including instructions for inputting the first word set, the second word set, and the first service usage review into a generative AI model and performing an operation of generating a second service usage review as a result of the input, The above user information is, Includes basic information of the guardian and basic information of the patient, The above care information is, Contains information on the above patient's disease, The above first evaluation score is, A value greater than or equal to the second evaluation score above, A system for generating service reviews.

10. In paragraph 9, The operation of obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score is as follows: An operation of calculating a first weighted score for the first evaluation score and a second weighted score for the second evaluation score; and An operation of obtaining the first word set corresponding to the first weighted score and the second word set corresponding to the second weighted score, The above first weighted score is, The value obtained by subtracting the average of the first evaluation score and the second evaluation score from the first evaluation score, The above second weighted score is, The value obtained by subtracting the above average from the above second evaluation score, The above first set of words is, Contains as many positive words as the number corresponding to the first weighted score above, The second set of words above is, Contains as many negative words as the number corresponding to the absolute value of the second weighted score, A system for generating service reviews.

11. In paragraph 9, The above generating action is, An action of receiving a request for modification of the second service usage review generated from the user terminal; In response to the received modification request, an operation of correcting the first evaluation score to obtain a first corrected evaluation score, and correcting the second evaluation score to obtain a second corrected evaluation score; An operation of inputting the first correction evaluation score and the second correction evaluation score into the emotional dictionary, and obtaining a third word set corresponding to the first correction evaluation score and a fourth word set corresponding to the second correction evaluation score; and An operation of inputting the third word set, the fourth word set, and the first service usage review into the generative AI model and regenerating the third service usage review as a result of the input, The above request for modification is, At least one of a first option for increasing the first evaluation score and the second evaluation score by a first set value and a second option for decreasing the first evaluation score and the second evaluation score by the first set value, A system for generating service reviews.

12. In paragraph 9, The above generating action is, An action of receiving a request for modification of the second service usage review generated from the user terminal; In response to the received modification request, an action of correcting the first evaluation score to obtain a first corrected evaluation score; An operation of inputting the first correction evaluation score into the above emotional dictionary and obtaining a third word set corresponding to the first correction evaluation score; and An operation of inputting the third word set, the second word set, and the first service usage review into the generative AI model and regenerating the third service usage review as a result of the input, The above request for modification is, At least one of a first option for increasing the first evaluation score by a first set value and a second option for decreasing the first evaluation score by the first set value, A system for generating service reviews.

13. Combined with a computing device, A step of obtaining a first service usage review having a similarity level higher than a standard value by using user information and nursing information of a nursing service used by the user; A step of obtaining a first evaluation score for a first evaluation item and a second evaluation score for a second evaluation item for the nursing service from a user terminal; A step of inputting the first evaluation score and the second evaluation score into an emotional dictionary for the previously generated nursing service evaluation items, and obtaining a first word set corresponding to the first evaluation score and a second word set corresponding to the second evaluation score; and A computer-readable recording medium storing a step of inputting the first word set, the second word set, and the first service usage review into a generative AI model and generating a second service usage review as a result of the input, The above user information is, Includes basic information of the guardian and basic information of the patient, The above care information is, Contains information on the above patient's disease, The above first evaluation score is, A value greater than or equal to the second evaluation score above, Computer program.

Images