Intelligent house dispatching method, device and equipment and storage medium

Abstract

The embodiment of the invention relates to the field of dormitory management, and discloses an intelligent room distribution method, device and equipment and a storage medium, and the method comprises the steps: building a generator used for dormitory distribution in a generative adversarial network, generating a dormitory distribution scheme based on the personal file of each user, and using the trained discriminator to discriminate whether the currently generated dormitory allocation scheme meets the requirements of the optimal dormitory allocation scheme, and if the currently generated dormitory allocation scheme meets the requirements of the optimal dormitory allocation scheme, outputting the current dormitory allocation scheme to complete dormitory allocation. According to the invention, residents with similar living habits and hobbies are arranged together, so that friction of the residents in daily life is reduced.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of dormitory management, and in particular to an intelligent room allocation method, device, equipment and storage medium. Background Art

[0002] How to allocate dormitories to avoid conflicts among roommates due to different living habits, improve the quality of life and satisfaction of residents, promote mental health, carry out common activities, enhance friendship and team spirit among dormitory members, and reflect respect and care for the individual needs of residents. This dormitory allocation method is of great significance for building a harmonious and friendly living environment. Summary of the invention

[0003] The purpose of the present invention is to at least provide an intelligent room allocation method, device, equipment and storage medium, which can at least solve the problem of how to allocate dormitories and improve the residents' satisfaction with the obtained dormitory allocation plan.

[0004] To solve the above technical problems, at least one embodiment of the present application provides an intelligent room assignment method, including:

[0005] Obtaining a personal profile of each resident, wherein the personal profile of the resident includes a hobby category and / or a living habit category to which the resident belongs;

[0006] According to the personal files of each resident, dormitory allocation is performed by using a preset generator for dormitory allocation to obtain a dormitory allocation plan;

[0007] The dormitory allocation plan is input into a pre-trained discriminator to obtain a discrimination result. When the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

[0008] In some optional embodiments, after the step of inputting the dormitory allocation plan into the pre-trained discriminator to obtain a discrimination result, the method further includes:

[0009] When the discrimination result is that the dormitory allocation plan does not meet the requirements of the optimal dormitory allocation plan, the satisfaction score of each resident on the current dormitory allocation plan is obtained, and based on the satisfaction score of each resident on the current dormitory allocation plan, the discriminator is trained again to obtain a newly trained discriminator; then the dormitory allocation plan newly generated by the generator is input into the newly trained discriminator to obtain a new discrimination result.

[0010] In some optional embodiments, training the discriminator includes: based on the satisfaction score of each resident on the dormitory allocation plan, training a support vector machine serving as the discriminator, to obtain the discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0011] In some optional embodiments, the generator performs dormitory allocation, including:

[0012] Extracting the hobby category and life habit category of each resident from the personal file of each resident;

[0013] Convert the extracted hobby categories and living habit categories of each household into numerical forms;

[0014] The hobby category and living habit category of each resident in numerical form are input into the generator to obtain a dormitory allocation plan.

[0015] In some optional embodiments, the personal file of the resident also includes the special disease needs of the resident, and the dormitory allocation by the generator according to the personal file of each resident includes:

[0016] Extracting the hobby category, life habit category and special disease needs of each resident from the personal files of each resident;

[0017] The households whose special disease needs are empty are regarded as first-category households, and the remaining households are regarded as second-category households;

[0018] Converting the extracted hobby categories and living habit categories of each first-category resident into numerical forms, and inputting the hobby categories and living habit categories of each first-category resident in numerical forms into the generator to obtain a dormitory allocation plan for the first-category resident;

[0019] Analyze the special disease needs of each of the extracted second-category residents, and obtain the special disease need category of each of the second-category residents;

[0020] Convert the hobby category, living habit category and special disease demand category of each second-category resident to numerical form, and input the hobby category, living habit category and special disease demand category of each second-category resident in numerical form into the generator to obtain a dormitory allocation plan for the second-category resident;

[0021] The dormitory allocation plan for the first category of residents and the dormitory allocation plan for the second category of residents are combined to obtain a dormitory allocation plan for all the residents.

[0022] In some optional embodiments, the process of establishing the personal profile of the resident includes:

[0023] Generate questionnaires based on preset hobby categories and lifestyle categories;

[0024] Obtaining the target residents' feedback on the questionnaire survey;

[0025] Determining the hobby category and life habit category of the target user according to the feedback results of the target household on the questionnaire survey;

[0026] A personal profile of the target user is generated according to the hobby category and the life habit category to which the target user belongs.

[0027] In some optional embodiments, the generator uses a K-means clustering algorithm to perform dormitory allocation.

[0028] At least one embodiment of the present application further provides an intelligent room dispatching device, comprising:

[0029] An acquisition module, used to acquire a personal profile of each resident, wherein the personal profile of the resident includes the hobby category and the living habit category of the resident;

[0030] A plan generation module, used to perform dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a dormitory allocation plan;

[0031] The discrimination module is used to input the dormitory allocation plan into a pre-trained discriminator to obtain a discrimination result. When the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

[0032] At least one embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent room assignment method.

[0033] At least one embodiment of the present application further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned intelligent room assignment method when executed by a processor.

[0034] The embodiments of the present application provide a method, device, equipment and storage medium for intelligent room assignment, which obtains the personal profile of each resident, including the hobby category and living habit category of the resident, and builds a generator for dormitory assignment in a generative adversarial network to generate a dormitory allocation plan based on the personal profile of each user, and uses a trained discriminator to determine whether the dormitory allocation plan generated at that time meets the requirements of the optimal dormitory allocation plan. When the judgment result is that it meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan at that time is output. Therefore, the intelligent room assignment method provided by this embodiment can arrange residents with similar living habits and similar hobbies together, which can reduce friction in the daily life of residents. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0036] Figure 1 is a flow chart of an intelligent room assignment method provided by an embodiment of the present application;

[0037] Figure 2 is a flow chart of an intelligent room assignment method provided by another embodiment of the present application;

[0038] Figure 3 is a structural schematic diagram of an intelligent room dispatching device provided by another embodiment of the present application;

[0039] Figure 4 It is a structural diagram of an intelligent room assignment device provided in another embodiment of the present application. DETAILED DESCRIPTION

[0040] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. However, it will be appreciated by those skilled in the art that in the present application, many technical details are proposed in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can also be implemented. The division of the following embodiments is for the convenience of description, and the specific implementation of the present application should not be construed as any limitation, and the various embodiments can be combined and referenced with each other under the premise of no contradiction.

[0041] Embodiment 1:

[0042] The intelligent room assignment method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 1 As shown, including:

[0043] Step S11, obtaining a personal profile of each resident, wherein the personal profile of the resident includes the hobby category and / or life habit category of the resident.

[0044] Specifically, the hobby category is one or more categories set according to personal preferences, such as a sports type who likes sports, a static type who likes static activities, a hobby type who likes calligraphy and other hobbies, etc. The life habit category is one or more categories set according to personal life habits, such as an early riser who likes to get up early, a night owl who likes to stay up late, a mysophobia type who values ​​cleanliness, a quiet type who prefers a quiet environment, a lively type who prefers a lively environment, etc.

[0045] The user's personal profile is established by collecting the user's accommodation demand information through text or voice, analyzing and identifying the collected accommodation demand information of the user, extracting key features of the user's accommodation demand, and generating the resident's personal profile.

[0046] In some examples, the process of establishing the resident's personal profile includes:

[0047] Step S111, generating a questionnaire survey according to preset hobby categories and life habit categories.

[0048] Specifically, the preset hobby categories and life habit categories can be used as options in the questionnaire. For example, the hobby categories are preset to include sports, calligraphy, and musical instruments. The life habit categories are preset to include early risers, late sleepers, and quiet environment. Based on this, the generated questionnaire can include: whether you like sports, calligraphy, musical instruments, whether you are used to getting up early, and whether you are used to sleeping late.

[0049] Step S112, obtaining the target household's feedback results on the questionnaire survey.

[0050] Specifically, the target household selects the options that match their characteristics according to the multiple-choice questions set in the questionnaire survey, and uses the selected results as feedback results. For example, the feedback results of user A are that they like sports, do not like calligraphy, like musical instruments, are not used to getting up early, and are used to going to bed late.

[0051] Step S113, determining the hobby category and life habit category of the target user according to the feedback results of the target household to the questionnaire survey.

[0052] For example, if the feedback result of user A is that he likes sports, dislikes calligraphy, likes musical instruments, is not used to getting up early, and is used to sleeping late, then the hobby categories of user A are sports type, non-calligraphy type, and musical instrument type, and the living habit categories of user A are late sleeping type and late waking type.

[0053] Step S114, generating a personal profile of the target user according to the hobby category and the living habit category to which the target user belongs.

[0054] Specifically, the target user is associated with the hobby category and the life habit category to which he belongs, so that the hobby category and the life habit category to which he belongs can be directly obtained based on the identity information that can represent the target user, such as the user name, user ID number, etc. For example, a user portrait can be generated, or an associated storage method can be used.

[0055] Step S12, performing dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a dormitory allocation plan.

[0056] Specifically, the generator may use a neural network model to perform dormitory allocation, or may use a clustering algorithm to implement dormitory allocation.

[0057] In one example, the generator uses a K-means clustering algorithm to perform dormitory allocation. The number of clusters K of the K-means clustering algorithm is determined based on the data of the dormitories to be allocated in actual situations and the capacity of each dormitory to be allocated, or is determined by experiments. Usually, when the generator uses a K-means clustering algorithm to perform dormitory allocation and obtains a dormitory allocation plan, it will be verified through manual analysis whether the hobby categories and living habit categories of the residents of each dormitory in the obtained dormitory allocation plan are close. It can be considered to use a greedy algorithm or other optimization algorithms to optimize the obtained dormitory allocation plan to ensure that the hobby categories and living habit categories of the residents in each dormitory are as similar as possible.

[0058] In some implementations, the step S12 includes:

[0059] Step S121, extracting the hobby category and life habit category of each resident from the personal file of each resident.

[0060] For example, there are user A and user B. User A's hobbies are sports, non-calligraphy, and musical instruments, and user A's living habits are late sleepers and late risers. User B's hobbies are sports, calligraphy, and non-musical instruments, and user B's living habits are late sleepers and early risers.

[0061] Step S122, convert the extracted hobby categories and living habit categories of each household into numerical form, so as to ensure that different hobby categories and living habit categories have a balanced impact on the clustering results. If necessary, standardization can also be performed after the conversion to numerical form.

[0062] Specifically, the numerical form can be in binary form or other numerical forms. Taking the binary form as an example, for example, the sports type corresponds to the numerical value 1, and the non-sports type corresponds to the numerical value 0. Still taking the aforementioned user A and user B as an example, the hobby categories of user A are sports type, non-calligraphy type and musical instrument type, and the living habit categories of user A are late sleep type and late rise type. The hobby types of user B are sports type, calligraphy type and non-musical instrument type, and the living habit categories of user B are late sleep type and early rise type. After the binary form conversion, user A corresponds to {1,0,1,0,0}, and user B corresponds to {1,1,0,0,1}.

[0063] Step S123, inputting the hobby category and living habit category of each resident in numerical form into the generator to obtain a dormitory allocation plan.

[0064] Step S13, input the dormitory allocation plan into a pre-trained discriminator to obtain a discrimination result. When the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, output the dormitory allocation plan to complete the dormitory allocation.

[0065] This embodiment obtains the personal profile of each resident, which includes the hobby category and / or living habit category of the resident, and builds a generator for dormitory allocation in a generative adversarial network to generate a dormitory allocation plan based on the personal profile of each user, and then uses a pre-trained discriminator to determine whether the dormitory allocation plan generated at that time meets the requirements of the optimal dormitory allocation plan. If it meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan at that time is output. Therefore, the intelligent room allocation method provided by this embodiment can arrange residents with similar living habits and similar hobbies together, which can reduce friction in the daily life of residents.

[0066] Embodiment 2:

[0067] The intelligent room assignment method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities. The specific process can be as follows: Figure 2 As shown, including:

[0068] Step S11, obtaining a personal profile of each resident, wherein the personal profile of the resident includes the hobby category and / or life habit category of the resident.

[0069] Specifically, the hobby category is one or more categories set according to personal preferences, such as a sports type who likes sports, a static type who likes static activities, a hobby type who likes calligraphy and other hobbies, etc. The life habit category is one or more categories set according to personal life habits, such as an early riser who likes to get up early, a night owl who likes to stay up late, a mysophobia type who values ​​cleanliness, a quiet type who prefers a quiet environment, a lively type who prefers a lively environment, etc.

[0070] The user's personal profile is established by collecting the user's accommodation demand information through text or voice, analyzing and identifying the collected accommodation demand information of the user, extracting key features of the user's accommodation demand, and generating the resident's personal profile.

[0071] In some examples, the process of establishing the resident's personal profile includes:

[0072] Step S111, generating a questionnaire survey according to preset hobby categories and life habit categories.

[0073] Specifically, the preset hobby categories and life habit categories can be used as options in the questionnaire. For example, the hobby categories are preset to include sports, calligraphy, and musical instruments. The life habit categories are preset to include early risers, late sleepers, and quiet environment. Based on this, the generated questionnaire can include: whether you like sports, calligraphy, musical instruments, whether you are used to getting up early, and whether you are used to sleeping late.

[0074] Step S112, obtaining the target household's feedback results on the questionnaire survey.

[0075] Specifically, the target household selects the options that match their characteristics according to the multiple-choice questions set in the questionnaire survey, and uses the selected results as feedback results. For example, the feedback results of user A are that they like sports, do not like calligraphy, like musical instruments, are not used to getting up early, and are used to going to bed late.

[0076] Step S113, determining the hobby category and life habit category of the target user according to the feedback results of the target household to the questionnaire survey.

[0077] For example, if the feedback result of user A is that he likes sports, dislikes calligraphy, likes musical instruments, is not used to getting up early, and is used to sleeping late, then the hobby categories of user A are sports type, non-calligraphy type, and musical instrument type, and the living habit categories of user A are late sleeping type and late waking type.

[0078] Step S114, generating a personal profile of the target user according to the hobby category and the living habit category to which the target user belongs.

[0079] Specifically, the target user is associated with the hobby category and the life habit category to which he belongs, so that the hobby category and the life habit category to which he belongs can be directly obtained based on the identity information that can represent the target user, such as the user name, user ID number, etc. For example, a user portrait can be generated, or an associated storage method can be used.

[0080] Step S12, performing dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a first dormitory allocation plan.

[0081] Specifically, the first dormitory allocation plan refers to the first dormitory allocation plan generated by the generator for allocating dormitories to the personal profile of each resident, and does not participate in the discriminant analysis of the subsequent discriminator.

[0082] The generator may use a neural network model to perform dormitory allocation, or may use a clustering algorithm to perform dormitory allocation.

[0083] Step S13, obtaining a satisfaction score of each resident on the first dormitory allocation plan.

[0084] Specifically, the satisfaction score of each resident on the first dormitory allocation plan is used to initially train the preset discriminator of the user to obtain a discriminator that can determine whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0085] Step S14: Based on the satisfaction score of each resident on the first dormitory allocation plan, a preset discriminator is trained to obtain a discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0086] In one implementation, the training of the preset discriminator includes: based on the satisfaction score of each resident on the dormitory allocation plan, training the support vector machine as the preset discriminator to obtain the discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0087] Step S15, performing dormitory allocation through the generator according to the personal profile of each resident to obtain a second dormitory allocation plan.

[0088] In one example, the generator uses a K-means clustering algorithm to perform dormitory allocation. The number of clusters K of the K-means clustering algorithm is determined based on the data of the dormitories to be allocated in actual situations and the capacity of each dormitory to be allocated, or is determined by experiments. Usually, when the generator uses a K-means clustering algorithm to perform dormitory allocation and obtains a dormitory allocation plan, it will be verified through manual analysis whether the hobby categories and living habit categories of the residents of each dormitory in the obtained dormitory allocation plan are close. It can be considered to use a greedy algorithm or other optimization algorithms to optimize the obtained dormitory allocation plan to ensure that the hobby categories and living habit categories of the residents in each dormitory are as similar as possible.

[0089] In some implementations, the step S15 of “allocating dormitories by the generator according to the personal profile of each resident” includes:

[0090] Step S151, extracting the hobby category and life habit category of each resident from the personal file of each resident.

[0091] For example, there are user A and user B. User A's hobbies are sports, non-calligraphy, and musical instruments, and user A's living habits are late sleepers and late risers. User B's hobbies are sports, calligraphy, and non-musical instruments, and user B's living habits are late sleepers and early risers.

[0092] Step S152, convert the extracted hobby categories and living habit categories of each household into numerical form, so as to ensure that different hobby categories and living habit categories have a balanced impact on the clustering results. If necessary, standardization processing can also be performed after the conversion to numerical form.

[0093] Specifically, the numerical form can be in binary form or other numerical forms. Taking the binary form as an example, for example, the sports type corresponds to the numerical value 1, and the non-sports type corresponds to the numerical value 0. Still taking the aforementioned user A and user B as an example, the hobby categories of user A are sports type, non-calligraphy type and musical instrument type, and the living habit categories of user A are late sleep type and late rise type. The hobby types of user B are sports type, calligraphy type and non-musical instrument type, and the living habit categories of user B are late sleep type and early rise type. After the binary form conversion, user A corresponds to {1,0,1,0,0}, and user B corresponds to {1,1,0,0,1}.

[0094] Step S153, inputting the hobby category and living habit category of each resident in numerical form into the generator to obtain a dormitory allocation plan.

[0095] Step S16, input the second dormitory allocation plan into the trained discriminator to obtain a discrimination result. If the discrimination result is that the second dormitory allocation plan does not meet the requirements of the optimal dormitory allocation plan, obtain the satisfaction score of each resident on the second dormitory allocation plan, and based on the satisfaction score of each resident on the second dormitory allocation plan, train the discriminator again, and then repeat steps S15 and S16; if the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, output the second dormitory allocation plan to complete the dormitory allocation.

[0096] In this embodiment, the personal profile of each resident is obtained, and the personal profile of the resident includes the hobby category and living habit category of the resident. By building a generator for dormitory allocation in a generative adversarial network, a dormitory allocation plan is generated based on the personal profile of each user, and then a discriminator capable of judging whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan is trained according to the satisfaction score of each resident on the previously generated dormitory allocation plan. Then, the trained discriminator is used to judge whether the dormitory allocation plan generated at that time meets the requirements of the optimal dormitory allocation plan. If not, the satisfaction score of each resident on the dormitory allocation plan at that time is obtained, and the discriminator is trained again based on the satisfaction score of each resident on the dormitory allocation plan at that time, and the generator is used again to generate a new dormitory allocation plan, and the newly trained discriminator is used to judge the newly generated dormitory allocation plan again until the judgment result meets the requirements of the optimal dormitory allocation plan, and the dormitory allocation plan at that time is output. Therefore, the intelligent room allocation method provided in this embodiment can arrange residents with similar living habits and similar hobbies together, which can reduce the friction in the daily life of residents.

[0097] Embodiment three:

[0098] The intelligent room assignment method of this embodiment can be applied to electronic devices with communication, computing and data storage capabilities, including:

[0099] Step S11, obtaining a personal file of each resident, wherein the personal file of the resident includes at least one of the resident's hobby category, living habit category, and special disease needs.

[0100] Specifically, the hobby category is one or more categories set according to personal preferences, such as a sports type who likes sports, a static type who likes static activities, a hobby type who likes calligraphy and other hobbies, etc. The living habit category is one or more categories set according to personal living habits, such as an early riser who likes to get up early, a night owl who likes to stay up late, a mysophobia type who pays attention to cleanliness, a quiet type who prefers a quiet environment, a lively type who prefers a lively environment, etc. The special disease needs refer to disease needs that require special care, such as special medical equipment, a special dormitory environment, etc.

[0101] The user's personal profile is established by collecting the user's accommodation demand information through text or voice, analyzing and identifying the collected accommodation demand information of the user, extracting key features of the user's accommodation demand, and generating the resident's personal profile.

[0102] In some examples, the process of establishing the resident's personal profile includes:

[0103] Step S111, generating a questionnaire survey according to preset hobby categories and life habit categories, wherein the questionnaire survey is provided with a column for filling in special disease requirements.

[0104] Specifically, the preset hobby categories and life habit categories can be used as options in the questionnaire. For example, the hobby categories are preset to include sports, calligraphy, and musical instruments. The life habit categories are preset to include early risers, late sleepers, and quiet environment. Based on this, the generated questionnaire can include: whether you like sports, calligraphy, musical instruments, whether you are used to getting up early, and whether you are used to sleeping late.

[0105] Step S112, obtaining the target household's feedback results on the questionnaire survey.

[0106] Specifically, the target household selects the options that suit their characteristics according to the multiple-choice questions set in the questionnaire survey, and uses the selected results as feedback results. For example, the feedback results of user A are that he likes sports, does not like calligraphy, likes musical instruments, is not used to getting up early, and is used to going to bed late. If user A has special disease needs, such as needing special medical equipment A, the feedback results of user A also include needing special medical equipment A.

[0107] Step S113, determining the hobby category and life habit category of the target user according to the feedback results of the target household to the questionnaire survey.

[0108] For example, if the feedback result of user A is that he likes sports, dislikes calligraphy, likes musical instruments, is not used to getting up early, and is used to sleeping late, then the hobby categories of user A are sports type, non-calligraphy type, and musical instrument type, and the living habit categories of user A are late sleeping type and late waking type.

[0109] Step S114, generating a personal profile of the target user according to the hobby category and the living habit category to which the target user belongs.

[0110] Specifically, the target user is associated with the hobby category and the life habit category to which he belongs, so that the hobby category and the life habit category to which he belongs can be directly obtained based on the identity information that can represent the target user, such as the user name, user ID number, etc. For example, a user portrait can be generated, or an associated storage method can be used.

[0111] Step S12, performing dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a first dormitory allocation plan.

[0112] Specifically, the first dormitory allocation plan refers to the first dormitory allocation plan generated by the generator for allocating dormitories to the personal profile of each resident, and does not participate in the discriminant analysis of the subsequent discriminator.

[0113] The generator may use a neural network model to perform dormitory allocation, or may use a clustering algorithm to perform dormitory allocation.

[0114] Step S13, obtaining a satisfaction score of each resident on the first dormitory allocation plan.

[0115] Specifically, the satisfaction score of each resident on the first dormitory allocation plan is used to initially train the preset discriminator of the user to obtain a discriminator that can determine whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0116] Step S14: Based on the satisfaction score of each resident on the first dormitory allocation plan, a preset discriminator is trained to obtain a discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0117] In one implementation, the training of the preset discriminator includes: based on the satisfaction score of each resident on the dormitory allocation plan, training the support vector machine as the preset discriminator to obtain the discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0118] Step S15, performing dormitory allocation through the generator according to the personal profile of each resident to obtain a second dormitory allocation plan.

[0119] In one example, the generator uses a K-means clustering algorithm to perform dormitory allocation. The number of clusters K of the K-means clustering algorithm is determined based on the data of the dormitories to be allocated in actual situations and the capacity of each dormitory to be allocated, or is determined by experiments. Usually, when the generator uses a K-means clustering algorithm to perform dormitory allocation and obtains a dormitory allocation plan, it will be verified through manual analysis whether the hobby categories and living habit categories of the residents of each dormitory in the obtained dormitory allocation plan are close. It can be considered to use a greedy algorithm or other optimization algorithms to optimize the obtained dormitory allocation plan to ensure that the hobby categories and living habit categories of the residents in each dormitory are as similar as possible.

[0120] In some implementations, the step S15 of “allocating dormitories by the generator according to the personal profile of each resident” includes:

[0121] Step S151, extracting the hobby category, living habit category and special disease needs of each resident from the personal file of each resident.

[0122] For example, there are user A, user B, user C, and user D. Among them, user A's hobbies are classified as sports, non-calligraphy, and musical instruments, and user A's living habits are classified as late sleepers and late risers. User B's hobbies are classified as sports, calligraphy, and non-musical instruments, and user B's living habits are classified as late sleepers and early risers. User C's hobbies are classified as non-sports, non-calligraphy, and musical instruments, and user C's living habits are classified as early sleepers and early risers, and user C's special disease needs are that they cannot be exposed to pollen. User D's hobbies are classified as sports, calligraphy, and musical instruments, and user D's living habits are classified as early sleepers and early risers, and user D's special disease needs are classified as requiring special medical equipment.

[0123] Step S152, the households whose special disease requirements are empty are regarded as first-category households, and the remaining households are regarded as second-category households.

[0124] Taking the above-mentioned user A, user B, user C and user D as an example, user A and user B are regarded as first-category households, and user C and user D are regarded as second-category households.

[0125] Step S153, convert the extracted hobby categories and living habit categories of each first-category resident to numerical form to ensure that different hobby categories and living habit categories have a balanced impact on the clustering results. If necessary, standardization processing can be performed after the conversion to numerical form. The hobby categories and living habit categories of each first-category resident in numerical form are also input into the generator to obtain the dormitory allocation plan for the first-category resident.

[0126] Specifically, the numerical form can be in binary form or other numerical forms. Taking the binary form as an example, for example, the sports type corresponds to the numerical value 1, and the non-sports type corresponds to the numerical value 0. Still taking the aforementioned user A and user B as an example, the hobby categories of user A are sports type, non-calligraphy type and musical instrument type, and the living habit categories of user A are late sleep type and late rise type. The hobby types of user B are sports type, calligraphy type and non-musical instrument type, and the living habit categories of user B are late sleep type and early rise type. After the binary form conversion, user A corresponds to {1,0,1,0,0}, and user B corresponds to {1,1,0,0,1}.

[0127] Step S154, analyzing the extracted special disease needs of each of the second-category households to obtain the special disease need categories of each of the second-category households.

[0128] For example, the special disease demand categories to which user C belongs are special equipment type and non-special environment type, and the special disease demand categories to which user D belongs are non-special equipment type and special environment type.

[0129] Step S155, converting the hobby category, living habit category and special disease need category of each second-category resident into numerical form, and inputting the hobby category, living habit category and special disease need category of each second-category resident in numerical form into the generator to obtain the dormitory allocation plan for the second-category residents.

[0130] Specifically, taking the binary form as an example, for example, the sports type corresponds to the value 1, and the non-sports type corresponds to the value 0. Still taking the aforementioned user C and user D as examples, the hobby categories of user C are non-sports, non-calligraphy, and musical instrument types, the living habits categories of user C are early to bed and early to rise, and the special disease needs categories of user C are special equipment and non-special environment types. The hobby categories of user D are sports, calligraphy, and musical instrument types, the living habits categories of user D are early to bed and early to rise, and the special disease needs categories of user D are non-special equipment and special environment types. After the binary form conversion, user C corresponds to {0,0,1,1,1,1,0}, and user D corresponds to {1,1,1,1,1,0,1}.

[0131] Step S156, merging the dormitory allocation plan for the first category of residents and the dormitory allocation plan for the second category of residents to obtain a dormitory allocation plan for all the residents.

[0132] Step S16, input the second dormitory allocation plan into the trained discriminator to obtain a discrimination result. If the discrimination result is that the second dormitory allocation plan does not meet the requirements of the optimal dormitory allocation plan, obtain the satisfaction score of each resident on the second dormitory allocation plan, and based on the satisfaction score of each resident on the second dormitory allocation plan, train the discriminator again, and then repeat steps S15 and S16; if the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, output the second dormitory allocation plan to complete the dormitory allocation.

[0133] In this embodiment, the personal profile of each resident is obtained, and the personal profile of the resident includes the hobby category, living habit category and special disease demand of the resident. By building a generator for dormitory allocation in a generative adversarial network, the personal profiles of the users with special disease demand and without special disease demand are divided into two batches, and dormitory allocation plans are generated by the generator, and the dormitory allocation plans generated in the two batches are merged to obtain the dormitory allocation plan of the current time. Then, according to the satisfaction score of each resident on the dormitory allocation plan generated last time, a discriminator capable of judging whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan is trained, and then the trained discriminator is used to judge whether the dormitory allocation plan generated this time meets the requirements of the optimal dormitory allocation plan. If not, the satisfaction score of each resident on the dormitory allocation plan of the current time is obtained, and the discriminator is trained again based on the satisfaction score of each resident on the dormitory allocation plan of the current time, and the generator is used again to generate a new dormitory allocation plan, and the newly trained discriminator is used to judge the newly generated dormitory allocation plan again until the judgment result meets the requirements of the optimal dormitory allocation plan, and the dormitory allocation plan of the current time is output. Therefore, the intelligent room allocation method provided in this embodiment can arrange residents with similar living habits and similar hobbies together, which can reduce friction in the daily lives of residents.

[0134] Embodiment 4:

[0135] Another embodiment of the present application relates to an intelligent room dispatching device. The implementation details of the intelligent room dispatching device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the intelligent room dispatching device of this embodiment can be as follows Figure 2 As shown, it includes an acquisition module 101, a solution generation module 102 and a determination module 103.

[0136] The acquisition module 101 is used to acquire the personal profile of each resident, and the personal profile of the resident includes the hobby category and / or life habit category of the resident.

[0137] Specifically, the hobby category is one or more categories set according to personal preferences, such as a sports type who likes sports, a static type who likes static activities, a hobby type who likes calligraphy and other hobbies, etc. The life habit category is one or more categories set according to personal life habits, such as an early riser who likes to get up early, a night owl who likes to stay up late, a mysophobia type who values ​​cleanliness, a quiet type who prefers a quiet environment, a lively type who prefers a lively environment, etc.

[0138] The user's personal profile is established by collecting the user's accommodation demand information through text or voice, analyzing and identifying the collected accommodation demand information of the user, extracting key features of the user's accommodation demand, and generating the resident's personal profile.

[0139] In some examples, the process of establishing the resident's personal profile includes:

[0140] Step S111, generating a questionnaire survey according to preset hobby categories and life habit categories.

[0141] Specifically, the preset hobby categories and life habit categories can be used as options in the questionnaire. For example, the hobby categories are preset to include sports, calligraphy, and musical instruments. The life habit categories are preset to include early risers, late sleepers, and quiet environment. Based on this, the generated questionnaire can include: whether you like sports, calligraphy, musical instruments, whether you are used to getting up early, and whether you are used to sleeping late.

[0142] Step S112, obtaining the target household's feedback results on the questionnaire survey.

[0143] Specifically, the target household selects the options that match their characteristics according to the multiple-choice questions set in the questionnaire survey, and uses the selected results as feedback results. For example, the feedback results of user A are that they like sports, do not like calligraphy, like musical instruments, are not used to getting up early, and are used to going to bed late.

[0144] Step S113, determining the hobby category and life habit category of the target user according to the feedback results of the target household to the questionnaire survey.

[0145] For example, if the feedback result of user A is that he likes sports, dislikes calligraphy, likes musical instruments, is not used to getting up early, and is used to sleeping late, then the hobby categories of user A are sports type, non-calligraphy type, and musical instrument type, and the living habit categories of user A are late sleeping type and late waking type.

[0146] Step S114, generating a personal profile of the target user according to the hobby category and the living habit category to which the target user belongs.

[0147] Specifically, the target user is associated with the hobby category and the life habit category to which he belongs, so that the hobby category and the life habit category to which he belongs can be directly obtained based on the identity information that can represent the target user, such as the user name, user ID number, etc. For example, a user portrait can be generated, or an associated storage method can be used.

[0148] The solution generation module 102 is used to perform dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a dormitory allocation solution.

[0149] Specifically, the generator generates the first dormitory allocation plan by performing the first dormitory allocation on the personal profile of each resident, which does not participate in the discriminant analysis of the subsequent discriminator, and is used to perform the first training of the subsequent discriminator using the satisfaction score of each resident on the first dormitory allocation plan. The generator can use a neural network model to perform dormitory allocation, or it can use a clustering algorithm to achieve dormitory allocation.

[0150] In one example, the generator uses a K-means clustering algorithm to perform dormitory allocation. The number of clusters K of the K-means clustering algorithm is determined based on the data of the dormitories to be allocated in actual situations and the capacity of each dormitory to be allocated, or is determined by experiments. Usually, when the generator uses a K-means clustering algorithm to perform dormitory allocation and obtains a dormitory allocation plan, it will be verified through manual analysis whether the hobby categories and living habit categories of the residents of each dormitory in the obtained dormitory allocation plan are close. It can be considered to use a greedy algorithm or other optimization algorithms to optimize the obtained dormitory allocation plan to ensure that the hobby categories and living habit categories of the residents in each dormitory are as similar as possible.

[0151] The discrimination module 103 is used to input the dormitory allocation plan into a pre-trained discriminator to obtain a discrimination result. When the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

[0152] Among them, dormitory allocation is performed by the generator according to the personal profile of each resident, which has been described in detail in the above embodiment and will not be repeated here.

[0153] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0154] Embodiment five:

[0155] Another embodiment of the present application relates to an intelligent room dispatching device. The implementation details of the intelligent room dispatching device of this embodiment are specifically described below. The following content is only for the convenience of understanding the implementation details, and is not necessary for the implementation of this solution. The schematic diagram of the intelligent room dispatching device of this embodiment can be as follows Figure 3 As shown, it includes a first acquisition module 201, a solution generation module 202, a second acquisition module 203, a training module 204 and a discrimination module 205.

[0156] The first acquisition module 201 is used to acquire a personal profile of each resident, wherein the personal profile of the resident includes the hobby category and / or life habit category of the resident.

[0157] Specifically, the hobby category is one or more categories set according to personal preferences, such as a sports type who likes sports, a static type who likes static activities, a hobby type who likes calligraphy and other hobbies, etc. The life habit category is one or more categories set according to personal life habits, such as an early riser who likes to get up early, a night owl who likes to stay up late, a mysophobia type who values ​​cleanliness, a quiet type who prefers a quiet environment, a lively type who prefers a lively environment, etc.

[0158] The user's personal profile is established by collecting the user's accommodation demand information through text or voice, analyzing and identifying the collected accommodation demand information of the user, extracting key features of the user's accommodation demand, and generating the resident's personal profile.

[0159] In some examples, the process of establishing the resident's personal profile includes:

[0160] Step S111, generating a questionnaire survey according to preset hobby categories and life habit categories.

[0161] Specifically, the preset hobby categories and life habit categories can be used as options in the questionnaire. For example, the hobby categories are preset to include sports, calligraphy, and musical instruments. The life habit categories are preset to include early risers, late sleepers, and quiet environment. Based on this, the generated questionnaire can include: whether you like sports, calligraphy, musical instruments, whether you are used to getting up early, and whether you are used to sleeping late.

[0162] Step S112, obtaining the target household's feedback results on the questionnaire survey.

[0163] Specifically, the target household selects the options that match their characteristics according to the multiple-choice questions set in the questionnaire survey, and uses the selected results as feedback results. For example, the feedback results of user A are that they like sports, do not like calligraphy, like musical instruments, are not used to getting up early, and are used to going to bed late.

[0164] Step S113, determining the hobby category and life habit category of the target user according to the feedback results of the target household to the questionnaire survey.

[0165] For example, if the feedback result of user A is that he likes sports, dislikes calligraphy, likes musical instruments, is not used to getting up early, and is used to sleeping late, then the hobby categories of user A are sports type, non-calligraphy type, and musical instrument type, and the living habit categories of user A are late sleeping type and late waking type.

[0166] Step S114, generating a personal profile of the target user according to the hobby category and the living habit category to which the target user belongs.

[0167] Specifically, the target user is associated with the hobby category and the life habit category to which he belongs, so that the hobby category and the life habit category to which he belongs can be directly obtained based on the identity information that can represent the target user, such as the user name, user ID number, etc. For example, a user portrait can be generated, or an associated storage method can be used.

[0168] The solution generation module 202 is used to perform dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a dormitory allocation solution.

[0169] Specifically, the generator generates the first dormitory allocation plan by performing the first dormitory allocation on the personal profile of each resident, which does not participate in the discriminant analysis of the subsequent discriminator, and is used to perform the first training of the subsequent discriminator using the satisfaction score of each resident on the first dormitory allocation plan. The generator can use a neural network model to perform dormitory allocation, or it can use a clustering algorithm to achieve dormitory allocation.

[0170] In one example, the generator uses a K-means clustering algorithm to perform dormitory allocation. The number of clusters K of the K-means clustering algorithm is determined based on the data of the dormitories to be allocated in actual situations and the capacity of each dormitory to be allocated, or is determined by experiments. Usually, when the generator uses a K-means clustering algorithm to perform dormitory allocation and obtains a dormitory allocation plan, it will be verified through manual analysis whether the hobby categories and living habit categories of the residents of each dormitory in the obtained dormitory allocation plan are close. It can be considered to use a greedy algorithm or other optimization algorithms to optimize the obtained dormitory allocation plan to ensure that the hobby categories and living habit categories of the residents in each dormitory are as similar as possible.

[0171] The second acquisition module 203 is used to obtain the satisfaction score of each resident with respect to the dormitory allocation plan.

[0172] The training module 204 trains a preset discriminator based on the satisfaction score of each resident on the previous dormitory allocation plan, and obtains a discriminator that can determine whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0173] In one implementation, the training of the preset discriminator includes: based on the satisfaction score of each resident on the dormitory allocation plan, training the support vector machine as the preset discriminator to obtain the discriminator capable of determining whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

[0174] The discrimination module 205 is used to input the dormitory allocation plan newly generated by the plan generation module into the discriminator newly trained by the training module to obtain a discrimination result. If the discrimination result is that the dormitory allocation plan does not meet the requirements of the optimal dormitory allocation plan, a new dormitory allocation plan is obtained from the plan generation module again, and a re-trained discriminator is obtained from the training module, and the obtained new dormitory allocation plan is input into the re-trained discriminator to obtain a new discrimination result. If the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

[0175] Among them, dormitory allocation is performed by the generator according to the personal profile of each resident, which has been described in detail in the above embodiment and will not be repeated here.

[0176] It is worth mentioning that all modules involved in this embodiment are logic modules. In practical applications, a logic unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed by this application, but this does not mean that there are no other units in this embodiment.

[0177] Embodiment six:

[0178] Another embodiment of the present application relates to an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent room assignment method in the above-mentioned embodiments.

[0179] Among them, the memory and the processor are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor.

[0180] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory can be used to store data used by the processor when performing operations.

[0181] Embodiment seven:

[0182] Another embodiment of the present application relates to a computer-readable storage medium storing a computer program, which implements the above method embodiment when executed by a processor.

[0183] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as: ROM), random access memory (Random Access Memory, referred to as: RAM), disk or optical disk and other media that can store program codes.

[0184] Those skilled in the art will appreciate that the above embodiments are specific embodiments for implementing the present application, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present application.

Claims

1. An intelligent room assignment method, characterized in that: include: Obtaining a personal profile of each resident, wherein the personal profile of the resident includes a hobby category and / or a living habit category to which the resident belongs; According to the personal files of each of the residents, dormitory allocation is performed through a preset generator for dormitory allocation to obtain a dormitory allocation plan; The dormitory allocation plan is input into a pre-trained discriminator to obtain a discrimination result. When the discrimination result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

2. The intelligent room assignment method according to claim 1, characterized in that: After the step of inputting the dormitory allocation plan into the pre-trained discriminator to obtain a discrimination result, the method further includes: When the discrimination result is that the dormitory allocation plan does not meet the requirements of the optimal dormitory allocation plan, the satisfaction score of each resident on the current dormitory allocation plan is obtained, and based on the satisfaction score of each resident on the current dormitory allocation plan, the discriminator is trained again to obtain a newly trained discriminator; then the dormitory allocation plan newly generated by the generator is input into the newly trained discriminator to obtain a new discrimination result.

3. The intelligent room assignment method according to claim 1 or 2, characterized in that: Training the discriminator includes: Based on the satisfaction score of each resident on the dormitory allocation plan, the support vector machine as the discriminator is trained to obtain the discriminator capable of discriminating whether the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan.

4. The intelligent room assignment method according to claim 1, characterized in that: The generator performs dormitory allocation, including: Extracting the hobby category and life habit category of each resident from the personal file of each resident; Convert the extracted hobby categories and living habit categories of each household into numerical forms; The hobby category and living habit category of each resident in numerical form are input into the generator to obtain a dormitory allocation plan.

5. The intelligent room assignment method according to claim 1, characterized in that: The personal file of the resident also includes the special disease needs of the resident. The dormitory allocation is performed by the generator according to the personal file of each resident, including: Extracting the hobby category, life habit category and special disease needs of each resident from the personal files of each resident; The households whose special disease needs are empty are regarded as first-category households, and the remaining households are regarded as second-category households; Converting the extracted hobby categories and living habit categories of each first-category resident into numerical forms, and inputting the hobby categories and living habit categories of each first-category resident in numerical forms into the generator to obtain a dormitory allocation plan for the first-category resident; Analyze the special disease needs of each of the extracted second-category residents, and obtain the special disease need category of each of the second-category residents; Convert the hobby category, living habit category and special disease demand category of each second-category resident to numerical form, and input the hobby category, living habit category and special disease demand category of each second-category resident in numerical form into the generator to obtain a dormitory allocation plan for the second-category resident; The dormitory allocation plan for the first category of residents and the dormitory allocation plan for the second category of residents are combined to obtain a dormitory allocation plan for all the residents.

6. The intelligent room assignment method according to claim 1, characterized in that: The process of establishing the personal file of the resident includes: Generate questionnaires based on preset hobby categories and lifestyle categories; Obtaining the target residents' feedback on the questionnaire survey; Determining the hobby category and / or life habit category of the target user according to the feedback results of the target household on the questionnaire survey; A personal profile of the target user is generated according to the hobby category and the life habit category to which the target user belongs.

7. The intelligent room assignment method according to claim 1, characterized in that: The generator uses K-means clustering algorithm to perform dormitory allocation.

8. An intelligent room dispatching device, characterized in that: include: An acquisition module, used to acquire a personal profile of each resident, wherein the personal profile of the resident includes a hobby category and / or a living habit category to which the resident belongs; A plan generation module, used to perform dormitory allocation according to the personal profile of each resident through a preset generator for dormitory allocation to obtain a dormitory allocation plan; The discriminant module is used to input the dormitory allocation plan into a pre-trained discriminator to obtain a discriminant result. When the discriminant result is that the dormitory allocation plan meets the requirements of the optimal dormitory allocation plan, the dormitory allocation plan is output to complete the dormitory allocation.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intelligent room assignment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent room assignment method described in any one of claims 1 to 7 is implemented.

Images