An employee dormitory management system, a control method thereof, and a storage medium

Abstract

The application discloses an employee dormitory management system and a control method thereof and a storage medium, and comprises the following steps: obtaining the personal identity information of a to-be-checked-in employee from a first terminal; sending the personal identity information to a second terminal and obtaining the approval result of the to-be-checked-in employee from the second terminal; inputting the personal identity information and the current dormitory state into a deep feature matching model in response to the approval result, obtaining the first score value, the second score value and the third score value between the employee and each bed; generating the matching degree between the employee and each bed according to the three score values; determining the bed number information of the employee according to the matching degree; sending the bed number information to the first terminal or updating the bed information and sending the updated bed information to the first terminal in response to the first operation instruction from the second terminal; and updating the current dormitory state in response to the second operation instruction from the first terminal. The application can improve the management efficiency and quality of employee dormitory allocation.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to an employee dormitory management system and its control method and storage medium. Background Technology

[0002] In modern enterprise management, employee dormitory management is a crucial component of human resource management and logistical support. As companies expand and the number of employees increases, traditional employee dormitory management methods face numerous challenges. Traditional dormitory allocation often relies on manual processes. For example, managers collect employee information using paper forms and then allocate beds based on their experience and limited understanding of the dormitory conditions. This method is inefficient. When processing a large volume of employee check-in information, manually organizing and allocating beds consumes significant time and effort, easily leading to slow check-in processes, hindering timely employee check-in, and reducing employee satisfaction with the company's logistical services.

[0003] Meanwhile, manual allocation struggles to fully consider individual employee differences and the precise matching of dormitory resources. Due to a lack of effective data integration and analysis tools, it's impossible to comprehensively assess the compatibility between employees' specific needs and the dormitory environment corresponding to each bed, leading to frequent instances of unreasonable dormitory allocation. For example, some employees may experience reduced rest quality and consequently, decreased work efficiency if their assigned beds do not suit their sleep habits. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes an employee dormitory management system, its control method, and storage medium, which can improve the management efficiency and quality of employee dormitory allocation.

[0005] Firstly, this application provides a control method for an employee dormitory management system, including:

[0006] Obtain the personal identification information of the employees waiting to check in from the first terminal;

[0007] The employee information is sent to the second terminal, and the approval result for the employee to be admitted is obtained from the second terminal;

[0008] In response to the approval result, the individual's identity information and current dormitory status are input into a preset deep feature matching model to obtain the first score, second score, and third score between the employee and each bed; wherein, the current dormitory status includes the bed information corresponding to each bed;

[0009] Based on the first score, the second score, and the third score, a matching degree between the employee and each bed is generated.

[0010] Based on the matching degree, the employee's bed number information is determined;

[0011] In response to a first operation command from the second terminal, the bed number information is sent to the first terminal, or the bed information is updated and the updated bed information is sent to the first terminal;

[0012] In response to a second operation command from the first terminal, the current dormitory status is updated.

[0013] The control method of the employee dormitory management system according to the first aspect of this application has at least the following beneficial effects: First, the personal identity information of the employee to be checked in is obtained from a first terminal. Then, the obtained personal identity information is sent to a second terminal so that the administrator can approve the employee's check-in application in the second terminal and generate a corresponding approval result. If the approval result is approved, the employee's personal identity information and the current dormitory status are input into a preset deep feature matching model. The current dormitory status includes the bed information corresponding to each bed. The deep feature matching model is used to obtain the first score, second score, and third score between the employee and each bed, which can quantitatively evaluate the suitability of the employee and the bed from multiple different dimensions. Then, these three scores are multiplied by their corresponding weights and added together to generate the matching degree between the employee and each bed. Based on the matching degree generated above, the system analyzes and evaluates the suitability of each bed and the employee, thereby determining the most suitable bed number information for the employee. Simultaneously, after generating the bed number information, a second terminal needs to confirm it. This terminal can directly confirm the system-assigned bed number information through a first operation command. If the assigned bed number information is deemed inappropriate, it can be modified using the first operation command before resubmitting. Employees perform specific operations on the first terminal, and upon receiving this command, the system recognizes that the employee has acknowledged and approved the assigned bed number information, thus completing this information exchange process. In this application, the entire process, from obtaining the identity information of the employee awaiting admission and the approval process to bed matching and allocation, is automated. For example, information is rapidly transmitted between the first terminal (employee's end) and the second terminal (management end), eliminating the need for manual processing and transmission of large amounts of paper documents or data tables, significantly saving time and labor costs. Furthermore, utilizing a pre-set deep feature matching model, a comprehensive analysis of a large amount of employee and dormitory bed information can be performed in a short time, quickly generating a matching score and determining the bed number information. Compared to the traditional method of manually evaluating and allocating beds one by one, this significantly improves the allocation speed. Furthermore, after the bed number information is generated, through the first operation command of the second terminal, the management personnel can adjust the system allocation results according to the actual situation. By combining manual and system methods, the matching results can be further optimized based on the model allocation, adapting to special situations or specific management needs of enterprises, and improving the accuracy and flexibility of matching.

[0014] According to some embodiments of the first aspect of this application, in response to the approval result, inputting the individual's identity information and current dormitory status into a preset deep feature matching model to generate a matching degree between the employee and each bed includes:

[0015] In response to the approval result, the individual's identity information and current dormitory status are input into a preset deep feature matching model to obtain the first score, second score and third score between the employee and each bed.

[0016] Based on the first score, the second score, and the third score, a matching degree between the employee and each bed is generated.

[0017] According to some embodiments of the first aspect of this application, the personal identity information includes basic information, project participation information, work performance information, and overtime pattern information, and the bed information includes safety assessment data for the area corresponding to each bed;

[0018] The individual's identity information and current dormitory status are input into a preset deep feature matching model to obtain the first score between the employee and each bed, including:

[0019] Categorical basic information and numerical basic information are extracted from the basic information;

[0020] The categorized basic information is processed by one-hot encoding and fully connected layer to obtain the first basic feature vector;

[0021] The numerical basic information is normalized and convolved to obtain the second basic feature vector;

[0022] The project participation information is combined and processed by a fully connected layer to obtain a project feature vector.

[0023] The work performance information is normalized and convolutionally processed to obtain a performance feature vector;

[0024] The overtime pattern information is periodically integrated and input into a preset time recurrent neural network to obtain an overtime feature vector;

[0025] The first basic feature vector and the second basic feature vector are concatenated to obtain a comprehensive basic feature vector. The project feature vector, the performance feature vector, and the overtime feature vector are combined to obtain a comprehensive work feature vector.

[0026] The security assessment data is normalized and convolutionally processed to obtain a security feature vector;

[0027] The comprehensive basic feature vector, comprehensive work feature vector, and safety feature vector are input into a preset first activation function to obtain the first score between the employee and each bed.

[0028] According to some embodiments of the first aspect of this application, the personal identity information includes personal hobbies information, personal social data information, and personal lifestyle information; the bed information includes the roommate identity information of the employee corresponding to other occupied beds in the same dormitory room for each bed; wherein, the roommate identity information includes roommate hobbies information, roommate social data information, and roommate lifestyle information.

[0029] The individual's identity information and current dormitory status are input into a preset deep feature matching model to obtain a second score between the employee and each bed, including:

[0030] The personal interest information, personal social data information, and personal lifestyle information are input into a preset large language model for semantic feature extraction to obtain personal interest feature vector, personal social data feature vector, and personal lifestyle feature vector.

[0031] The roommate's hobbies, social data, and lifestyle information are input into the large language model for semantic feature extraction, resulting in roommate hobbies feature vector, roommate social data feature vector, and roommate lifestyle feature vector.

[0032] The similarity of the personal interest feature vector and the roommate's interest feature vector, the personal social data feature vector and the roommate's social data feature vector, and the personal lifestyle feature vector and the roommate's lifestyle feature vector are calculated respectively to obtain the first similarity, the second similarity and the third similarity.

[0033] Based on the first similarity, the second similarity, and the third similarity, a second score is obtained between the employee and each bed.

[0034] According to some embodiments of the first aspect of this application, the personal identity information includes bed preference information and demand information, and the bed information includes the location information corresponding to each bed and the room information of the dormitory room in which it is located;

[0035] The individual's identity information and current dormitory status are input into a preset deep feature matching model to obtain a third score between the employee and each bed, including:

[0036] The bed preference information is classified to obtain a preference feature vector;

[0037] The demand information, the location information, and the room information are each subjected to one-hot encoding to obtain demand feature vector, location feature vector, and room feature vector;

[0038] The preference feature vector and the demand feature vector are concatenated to obtain a comprehensive demand feature vector;

[0039] The location feature vector and the room feature vector are concatenated to obtain the comprehensive room feature vector;

[0040] The comprehensive feature vector of demand and the comprehensive feature vector of room are input into a preset classifier model and processed for decision-making to obtain the third score between employees and each bed.

[0041] According to some embodiments of the first aspect of this application, it also includes:

[0042] Obtain the energy consumption in the dormitory rooms;

[0043] In response to a first setting command from the second terminal, an energy consumption cost gradient comparison table is set.

[0044] Based on the energy consumption and energy consumption cost gradient comparison table, energy payment items are obtained;

[0045] The energy payment item is added to the preset bill and sent to the first terminal;

[0046] In response to a payment completion instruction from the first terminal, the energy payment item corresponding to the payment completion instruction is deleted from the billing statement.

[0047] According to some embodiments of the first aspect of this application, after the step of obtaining the energy consumption in the dormitory room, the method further includes:

[0048] In response to a second setting instruction from the first terminal or the second terminal, an energy consumption threshold is set;

[0049] When the energy consumption is greater than or equal to the energy consumption threshold, an energy consumption warning notification is sent to the first terminal.

[0050] According to some embodiments of the first aspect of this application, it also includes:

[0051] Acquire real-time temperature, humidity, and light levels in multiple dormitory rooms;

[0052] Based on the multiple real-time temperature values, multiple real-time humidity values, and multiple real-time light sensitivity values, the average temperature value, average humidity value, and average light sensitivity value are obtained.

[0053] In response to a third setting command from the first terminal or the second terminal, the temperature threshold range, humidity threshold range, and light sensitivity threshold range are set.

[0054] When the average temperature value is outside the temperature threshold range, a first control command is sent to the electrical equipment in the corresponding dormitory room until the average temperature value is within the temperature threshold range, at which point a first stop command is sent to the electrical equipment in the corresponding dormitory room.

[0055] When the average humidity value is outside the humidity threshold range, a second control command is sent to the electrical equipment in the corresponding dormitory room until the average humidity value is within the humidity threshold range, at which point a second stop command is sent to the electrical equipment in the corresponding dormitory room.

[0056] When the average light sensitivity value is outside the light sensitivity threshold range, a third control command is sent to the electrical equipment in the corresponding dormitory room until the average light sensitivity value is within the light sensitivity threshold range, at which point a third stop command is sent to the electrical equipment in the corresponding dormitory room.

[0057] Secondly, this application also provides an employee dormitory management system, including:

[0058] At least one memory;

[0059] At least one processor;

[0060] At least one program;

[0061] The program is stored in the memory, and the processor executes at least one of the programs to implement the control method of the employee dormitory management system as described in any embodiment of the first aspect.

[0062] Thirdly, this application also provides a computer-readable storage medium storing computer-executable signals for performing a control method for an employee dormitory management system as described in any embodiment of the first aspect.

[0063] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0064] Additional aspects and advantages of this application will become apparent and readily understood in conjunction with the following description of the embodiments, in which:

[0065] Figure 1 A flowchart illustrating the control method of the employee dormitory management system provided in the first embodiment of this application;

[0066] Figure 2 For this application Figure 1 A flowchart for calculating the first score;

[0067] Figure 3 For this application Figure 1 A flowchart for calculating the second score;

[0068] Figure 4 For this application Figure 1 A flowchart for calculating the third fraction;

[0069] Figure 5 A flowchart illustrating the control method of the employee dormitory management system provided in the second embodiment of this application;

[0070] Figure 6 For this application Figure 5 Flowchart following step S510;

[0071] Figure 7 A flowchart of the control method for the employee dormitory management system provided in the third embodiment of this application. Detailed Implementation

[0072] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0073] In the description of this application, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application.

[0074] In the description of this application, the use of "first" and "second" is for the purpose of distinguishing technical features only, and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0075] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0076] First, let's analyze some of the terms used in this application:

[0077] One-hot encoding, also known as single-bit encoding, is a data encoding method primarily used for processing categorical data. In categorical data, variables typically have multiple categories, and the purpose of one-hot encoding is to convert these categorical variables into a numerical form that machine learning algorithms can better understand.

[0078] A fully connected layer is a fundamental layer structure in artificial neural networks. In this layer, every neuron is fully connected to all neurons in the previous layer, meaning that the output of each neuron in the previous layer is used as a weight input to every neuron in the current layer. It is primarily used for integrating and classifying extracted features, and is a crucial part of deep neural networks in making final decisions or generating high-level feature representations.

[0079] Normalization is a data preprocessing technique used to transform the feature values ​​of data to a specific range, typically [0,1] or [-1,1]. Its purpose is to eliminate differences in units and value ranges between different features, allowing data to be processed on a uniform scale, improving data quality, and ultimately enhancing the performance of machine learning models.

[0080] Recurrent Neural Networks (RNNs) are a type of neural network specifically designed for processing sequential data. Sequential data refers to data points arranged in a time or other order, such as time series data (e.g., stock price changes over time, waveforms of speech signals arranged in chronological order), and text data (the order of words in a sentence). Unlike traditional feedforward neural networks, RNNs have recurrent connections, allowing them to utilize information from previously processed elements when processing each element in the sequence.

[0081] Large Language Models (LLMs), from a semantic extraction perspective, are tools trained on massive amounts of text data. Their Transformer architecture's attention mechanism dynamically focuses on relevant content, effectively capturing semantic relationships. Through a multi-layered structure, they automatically extract semantic features at various levels, from lexical to pragmatic, transforming text into semantic vectors. They can accurately understand semantics based on context and generate coherent text, and can also mine deep semantics, adapting across domains and extracting semantics to handle various tasks.

[0082] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0083] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0084] The control method for an employee dormitory management system provided in this application relates to the field of artificial intelligence technology. This control method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the control method for the employee dormitory management system, but is not limited to the above forms.

[0085] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0086] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards of the relevant countries and regions. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirects to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data for the proper functioning of the embodiments of this application obtained.

[0087] Firstly, this application provides a control method for an employee dormitory management system, which may include, but is not limited to, the following steps:

[0088] Step S110: Obtain the personal identification information of the employee to be checked in from the first terminal;

[0089] Step S120: Send your personal identification information to the second terminal and obtain the approval result for the employee to be admitted from the second terminal;

[0090] Step S130: In response to the approval result, input the employee's identity information and current dormitory status into the preset deep feature matching model to obtain the first score, second score and third score between the employee and each bed; wherein, the current dormitory status includes the bed information corresponding to each bed;

[0091] Step S140: Generate the matching degree between employees and each bed based on the first score, the second score, and the third score;

[0092] Step S150: Determine the employee's bed number information based on the matching degree;

[0093] Step S160: In response to the first operation command from the second terminal, send the bed number information to the first terminal, or update the bed information and send the updated bed information to the first terminal;

[0094] Step S170: In response to the second operation command from the first terminal, update the current dormitory status.

[0095] It should be noted that the first terminal can be a mobile device used by employees to submit check-in applications or an application terminal designated by the company, while the second terminal can be a terminal device used by management personnel responsible for dormitory management and approval, such as a computer-based management system. This application does not make any specific restrictions on this.

[0096] In steps S110 to S160, firstly, the identity information of the employee to be checked in is obtained from the first terminal. Then, the obtained identity information is sent to the second terminal so that the administrator can approve the employee's check-in application and generate a corresponding approval result. If the approval result is successful, the employee's identity information and the current dormitory status are input into a preset deep feature matching model. The current dormitory status includes the bed information for each bed. Through the calculation of the deep feature matching model, considering relevant factors in the employee's identity information and the characteristics of the bed information, a matching degree between the employee and each bed is generated. Based on the generated matching degree, the system analyzes and evaluates the suitability of each bed and the employee, thereby determining the most suitable bed number for the employee. Simultaneously, after generating the bed number information, the second terminal needs to confirm the bed number information. It can directly confirm the bed number information assigned by the system through a first operation command; if it feels that the bed number information assigned by the system is inappropriate, it can also modify the bed number information through the first operation command before sending it. Employees perform specific operations on a primary terminal. Upon receiving this instruction, the system recognizes that the employee has acknowledged and approved the assigned bed number, thus completing this information exchange process. In this application, the entire process, from obtaining the identity information of the employee awaiting admission and the approval process to bed matching and allocation, is automated. For example, information is rapidly transferred between the primary terminal (employee's end) and the secondary terminal (management end), eliminating the need for manual processing and transmission of numerous paper documents or data tables, significantly saving time and labor costs. Furthermore, utilizing a pre-set deep feature matching model, a comprehensive analysis of large amounts of employee and dormitory bed information can be performed quickly, rapidly generating a matching score and determining the bed number. Compared to the traditional method of manually evaluating and allocating beds one by one, this significantly improves allocation speed. Moreover, after the bed number information is generated, through the first operation instruction on the secondary terminal, managers can adjust the system allocation results according to the actual situation. By combining manual and system methods, the matching results can be further optimized based on the model allocation, adapting to special circumstances or specific management needs of the enterprise, improving the accuracy and flexibility of the matching.

[0097] It should be noted that there can be multiple secondary terminals, and each terminal must agree and approve before bed allocation can be made for an employee; alternatively, the first secondary terminal may approve the allocation before the employee's identity information is sent to the second secondary terminal for verification. In other words, multiple secondary terminals must sequentially complete their approvals before bed allocation can be made. The specific approval method can be determined based on the company's specific management structure. This multi-terminal sequential approval method can fully leverage the functional advantages of each department, comprehensively considering employee check-in applications from multiple dimensions, thereby maximizing the rationality, compliance, and fairness of dormitory allocation and avoiding erroneous decisions or unreasonable allocations that may result from the limitations of a single department's review.

[0098] In step S150, under certain circumstances, managers may deem the bed numbering information assigned by the system inappropriate based on their comprehensive consideration of the overall dormitory layout and personnel arrangements. For example, dispersing employees from the same department may hinder teamwork and communication, or certain special beds (such as those near public facilities that might cause noise pollution, but the system has not fully considered the sensitivity of specific employees) may be assigned to unsuitable employees. Managers can modify the bed numbering information using the relevant operation functions of the second terminal and the first operation command. For example, they can reselect a bed number that is more suitable for the specific employee's needs or conforms to the overall dormitory arrangement plan. After completing the modification, the first operation command is sent through the second terminal to send the modified bed number information to the first terminal, ensuring that employees receive accurate and appropriate bed allocation results. In this step, bed allocation not only relies on the system's automatic matching model but also incorporates the manager's experience and judgment based on actual conditions. This ensures both the efficiency of the system's automatic matching and the scientific nature of considering multiple factors, while also allowing for flexible adjustments based on specific scenarios when necessary, further improving the rationality of bed allocation and meeting the diverse needs of enterprises in dormitory management.

[0099] In step S160, the system can clearly determine whether the employee has received and approved the allocation result, avoiding uncertainty in the information transmission process and ensuring effective feedback at every stage. The employee's confirmation of the bed number information serves as the second operation instruction, forming a complete closed loop in the entire information transmission process. Only after the employee confirms the bed number information can the system consider this allocation as the final valid allocation and perform subsequent related dormitory status updates (such as marking the bed as occupied). This confirmation operation is crucial to ensuring the smooth progress of the entire dormitory allocation process according to the predetermined plan, preventing subsequent management chaos that may occur due to the employee's failure to confirm, such as duplicate bed allocations.

[0100] In steps S130 to S140, a deep feature matching model is used to derive the first, second, and third scores between employees and each bed, enabling a quantitative assessment of employee-bed suitability from multiple dimensions. Different weights can be assigned to the first, second, and third scores, with the weight depending on the relative importance of the factor represented by each score in the overall matching evaluation. These three scores are then multiplied by their corresponding weights and summed to obtain the final matching degree.

[0101] Understandably, personal identification information includes basic information, project participation information, work performance information, and overtime work pattern information. Bed information includes safety assessment data for the area corresponding to each bed. The aforementioned basic information can include name, gender, age, position, place of origin, marital status, and job code, etc. Project participation information can include project type, project duration, and project urgency, etc. Overtime work pattern information can include average weekly overtime hours and overtime time distribution, etc. Among the basic information, information such as gender, place of origin, and marital status can be categorized as categorized basic information, while age and job code can be categorized as numerical basic information.

[0102] Reference Figure 2 It is understandable that the step of inputting the employee's identity information and current dormitory status into a preset deep feature matching model to obtain the first score between the employee and each bed may include, but is not limited to, the following steps:

[0103] Step S310: Extract categorical basic information and numerical basic information from the basic information;

[0104] Step S320: Perform one-hot encoding and fully connected layer processing on the basic information of the classification to obtain the first basic feature vector;

[0105] Step S330: Normalize and convolve the numerical basic information to obtain the second basic feature vector;

[0106] Step S340: Combine the project participation information and process it with a fully connected layer to obtain the project feature vector;

[0107] Step S350: Normalize and convolution the work performance information to obtain the performance feature vector;

[0108] Step S360: Periodically integrate the overtime work pattern information and input it into a preset time recurrent neural network to obtain the overtime work feature vector;

[0109] Step S370: Concatenate the first basic feature vector and the second basic feature vector to obtain the comprehensive basic feature vector, and combine the project feature vector, performance feature vector and overtime feature vector to obtain the comprehensive work feature vector.

[0110] Step S380: Normalize and convolutionally process the security assessment data to obtain the security feature vector;

[0111] Step S390: Input the comprehensive basic feature vector, comprehensive work feature vector, and safety feature vector into the preset first activation function to obtain the first score between the employee and each bed.

[0112] In one embodiment, during steps S310 to S390 described above, the input of basic information can be:

[0113] Name Li Ming gender male age 30 years old Position Software Engineer Place of origin Shenzhen, Guangdong Marital status Married

[0114] The project involvement information indicates that the individual is currently involved in a large-scale artificial intelligence project, expected to last one year, which is a key and urgent project for the company. In the past year, the individual participated in three medium-sized software development projects, with durations of 3 months, 5 months, and 4 months respectively.

[0115] The work performance information shows that the performance evaluation results for the past three months are 90, 88 and 92 points respectively (out of 100). The amount of tasks completed in the project is among the top in the team, and the code quality is high with a low defect rate.

[0116] The information regarding overtime patterns indicates that the average weekly overtime hours are approximately 10 hours, with the overtime period mainly concentrated between 7 PM and 10 PM from Tuesday to Thursday.

[0117] In the processing, basic information such as "gender (male), place of origin (Shenzhen, Guangdong), and marital status (married)" is encoded using one-hot encoding and then mapped through a fully connected layer. For example, these encoded vectors are input into a fully connected layer with 32 neurons and activated using the ReLU activation function. Assuming that this layer produces a 32-dimensional feature vector, where some dimensions may represent abstract representations of factors such as male, married, or from a specific region in the model. Additionally, for the numerical basic information "age (30 years old) and job title (software engineer)," since job title can be categorized (e.g., 1 represents software engineer, 2 represents hardware engineer, etc.), it is normalized along with age and then processed using a small CNN to extract features. For example, age and job title are encoded into a time-series-like data set (e.g., [30,1]), convolved with a 3x1 kernel to extract local features, then reduced in dimensionality by max pooling (2x1 kernel) and connected to a 64-neuron fully connected layer activated by ReLU. This layer may extract the characteristics of the combination of age and job position in relation to dormitory needs. For example, young software engineers may have higher requirements for dormitory network facilities. The model learns to reflect this feature association on certain neurons.

[0118] For project participation, a vector (e.g., [3, 12, 3, 12]) is created by combining data such as the urgency of the current project (assuming a key and urgent project is coded as 3), the expected duration (1 year is coded as 12), the number of past projects participated in (3), and the total duration (3+5+4=12 months, coded as 12). Feature mapping is performed through a fully connected layer with 32 neurons and the ReLU activation function. This layer can learn the characteristics of dormitory needs related to the complexity and persistence of project participation. For example, employees who participate in multiple projects for a long time may need a more comfortable rest environment to alleviate work pressure, and the model will reflect this relationship on some neurons.

[0119] Regarding work performance information, the average of performance evaluation results over the past three months ((90+88+92) / 3=90) is calculated and combined with information such as task completion volume and code quality (assuming task completion volume is among the top in the team, encoded as 2, and high code quality is encoded as 3), forming a vector (e.g., [90,2,3]). After normalization, feature extraction is performed using a convolutional neural network (CNN), for example, using a 2x1 convolution kernel to perform convolution operations on the data to extract local features. Then, after dimensionality reduction by a pooling layer (e.g., max pooling, 2x1 kernel), it is connected to a 32-neuron fully connected layer using the ReLU activation function. This step can extract the potential relationship between performance and dormitory demand.

[0120] For overtime patterns, data is organized according to a seven-day week, such as [0,10,10,10,0,0,0] (representing 10 hours of overtime from Tuesday to Thursday, with no overtime at other times). This data is then input into a recurrent neural network, specifically an LSTM (Long Short-Term Memory) network. The LSTM learns the periodicity and duration of overtime, and its output is connected to a 32-neuron fully connected layer and a ReLU activation function. This may yield feature representations regarding employee overtime habits and their needs for dormitory location (e.g., proximity to the company to reduce commuting fatigue) or dormitory facilities (e.g., the need for better soundproofing for rest after overtime).

[0121] The overall safety assessment data of the dormitory area is obtained from the bed information, assuming a safety score of 8 out of 10. This data is normalized and then used for feature mapping through an additional fully connected layer, for example, with 16 neurons and the ReLU activation function. This layer learns the influence of the safety assessment data on employee matching characteristics. For example, for Li Ming, who is involved in key projects, a higher safety assessment may show a positive matching tendency on certain neurons. This feature vector is then concatenated with the vectors processed from the basic information and work characteristics to form a comprehensive feature vector for subsequent matching degree calculations.

[0122] The feature vectors obtained through the different processing steps are concatenated to form a comprehensive feature vector. Assume the concatenated vector is (32+64+32+32+32+16=208) dimensional. Then, a fully connected layer with only one neuron is used to calculate the matching degree. This fully connected layer calculates the first score of the employee's basic and work-related feature branches relative to a specific bed location based on the extracted features.

[0123] The processing of various information types, the construction of feature vectors, and the generation of scores throughout the process provide rich data-driven decision-making support for dormitory management. Managers can analyze these feature vectors and scores to understand the overall characteristics and demand distribution of the employee group. For example, if it is found that employees participating in a certain type of project generally have higher first-score scores in a particular bed area, it indicates that the bed resource allocation in that area is relatively reasonable in meeting the needs of these employees. This can serve as a reference for subsequent resource planning and adjustments, helping managers to formulate more scientific and reasonable dormitory management strategies and resource optimization plans.

[0124] Understandably, personal identity information includes personal hobbies, social data, and lifestyle habits. Bed information includes the roommate information of the employee whose other beds in the same dormitory room are occupied. Among these, roommate identity information includes roommate hobbies, social data, and lifestyle habits.

[0125] The step of inputting the employee's personal information and current dormitory status into a preset deep feature matching model to obtain the second score between the employee and each bed may include, but is not limited to, the following steps:

[0126] Step S410: Input personal interest information, personal social data information, and personal lifestyle information into a preset large language model for semantic feature extraction to obtain personal interest feature vector, personal social data feature vector, and personal lifestyle feature vector;

[0127] Step S420: Input the roommate's hobbies, social data, and lifestyle information into the large language model for semantic feature extraction to obtain the roommate's hobbies feature vector, social data feature vector, and lifestyle feature vector.

[0128] Step S430: Perform similarity calculations on the feature vectors of my own interests and hobbies and those of my roommates, the feature vectors of my own social data and those of my roommates, and the feature vectors of my own living habits and those of my roommates to obtain the first similarity, the second similarity, and the third similarity.

[0129] Step S440: Based on the first similarity, second similarity and third similarity, obtain the second score between the employee and each bed.

[0130] In steps S410 to S440, in one embodiment, Li Ming filled in "likes reading science fiction novels, loves outdoor sports, especially mountain climbing, and is passionate about photography" in the hobbies section. These hobbies are input into a pre-trained large language model. The large language model performs semantic understanding and analysis, for example, extracting feature dimensions related to imagination and knowledge exploration for the hobby of reading science fiction novels, feature dimensions related to physical fitness and adventurous spirit for the hobby of mountain climbing, and feature dimensions related to light and composition perception for the hobby of photography, thus forming a comprehensive personal hobby feature vector. Similarly, through semantic understanding and analysis by the large language model, personal social data feature vectors and personal lifestyle habit feature vectors are obtained respectively.

[0131] Subsequently, using the same method, feature vectors of roommates' interests, social data, and lifestyle habits were calculated. By extracting the personal and roommate interest feature vectors and calculating the first similarity, employees with similar interests can be grouped together. A second similarity calculation using the personal and roommate social data feature vectors considers employees' social behavior patterns and social circle characteristics when allocating beds. Finally, by extracting the personal and roommate lifestyle habit feature vectors and calculating the third similarity, rooming employees with similar lifestyle habits helps maintain a clean and hygienic dormitory environment, reduces friction and disputes caused by differences in lifestyle habits, and makes employee dormitory life more comfortable and relaxed.

[0132] The second score is obtained by combining the similarity calculation results of various feature vectors, providing a quantitative basis for bed allocation decisions. Managers can intuitively judge the compatibility between employees and different beds (based on roommate situations) based on this score, thus making more scientific bed allocation decisions. This data-driven approach reduces the subjectivity and uncertainty of human judgment, making dormitory management more standardized and intelligent, and improving management efficiency and decision-making quality.

[0133] Understandably, the personal identification information includes bed preference information and demand information. Bed information includes the location information corresponding to each bed and the room information of the dormitory room. Among them, the location information corresponding to each bed can include the floor where the bed is located, the orientation of the bed, and the bunk bed configuration, etc. The room information can include the room size, maximum number of occupants, bathroom facilities, and electrical appliances.

[0134] The step of inputting the employee's personal information and current dormitory status into a preset deep feature matching model to obtain the third score between the employee and each bed may include, but is not limited to, the following steps:

[0135] Step S510: Classify the bed preference information to obtain the preference feature vector;

[0136] Step S520: Perform one-hot encoding on the demand information, location information, and room information respectively to obtain the demand feature vector, location feature vector, and room feature vector;

[0137] Step S530: Concatenate the preference feature vector and the demand feature vector to obtain the comprehensive demand feature vector;

[0138] Step S540: Concatenate the location feature vector and the room feature vector to obtain the comprehensive room feature vector;

[0139] Step S550: Input the demand comprehensive feature vector and the room comprehensive feature vector into the preset classifier model and perform decision processing to obtain the third score value between the employee and each bed.

[0140] In steps S510 to S550, preference feature vectors are obtained by classifying bed preference information, which can accurately capture employees' specific needs and preferences for beds. For example, some employees may prefer beds on higher floors for better views and ventilation, or prefer lower bunks for easier movement. Converting this preference information into feature vectors and incorporating them into the matching model can significantly increase the probability of bed allocation meeting employee expectations, allowing employees to feel respected and satisfied with their individual needs upon check-in, thereby improving employee satisfaction with dormitory arrangements and their positive feelings towards the company. In addition to bed preferences, demand information (such as whether they need to be near a window for studying or working, or whether they need a quiet environment) is processed using one-hot encoding to obtain demand feature vectors, which are then concatenated with preference feature vectors to form a comprehensive demand feature vector. This allows the model to comprehensively consider employees' various accommodation needs, not just limited to the bed itself, but also including the needs of the surrounding environment and facilities. For example, assigning employees who need to study online or work remotely in their dormitories to rooms with stable network signals, beds near windows, and ample natural light will greatly improve their learning and work efficiency and comfort, further enhancing the compatibility between employees, beds, and the dormitory environment. The classifier model can be a machine learning model such as a support vector machine or decision tree. Based on pre-trained parameters and algorithms, the classifier model analyzes and makes decisions on two input feature vectors. After calculation, the model outputs a third-score value representing the degree of matching between the employee and each bed. This third-score value can be a value between 0 and 1; a higher value indicates a higher degree of matching between the employee and the bed in terms of needs and room conditions.

[0141] The entire process operates based on a pre-defined deep feature matching model and classifier model, enabling intelligent decision-making for dormitory bed allocation. Through in-depth analysis and processing of employee identity information and dormitory status information, the model automatically generates a third-score value between employees and each bed, reducing the subjectivity and arbitrariness of manual bed allocation. This intelligent decision-making mechanism can quickly process large amounts of employee and dormitory data, improving the efficiency and accuracy of bed allocation and making dormitory management more scientific, standardized, and efficient.

[0142] It is understood that the control method of the employee dormitory management system provided in this application may also include, but is not limited to, the following steps:

[0143] Step S610: Obtain the energy consumption in the dormitory room;

[0144] Step S620: In response to the first setting command from the second terminal, set the energy consumption cost gradient comparison table;

[0145] Step S630: Based on the energy consumption and energy cost gradient comparison table, obtain the energy payment details;

[0146] Step S640: Add the energy payment item to the preset bill and send it to the first terminal;

[0147] Step S650: In response to the payment completion instruction from the first terminal, delete the energy payment item corresponding to the payment completion instruction from the billing statement.

[0148] In steps S610 to S650, the system connects to or collects data from relevant energy metering devices (such as electricity meters and water meters) in the dormitory rooms to obtain real-time energy consumption data for each dormitory room. These devices can periodically transmit energy usage information to the dormitory management system. For example, electricity meters send electricity consumption data for a given period at regular intervals (e.g., hourly, daily), and water meters similarly upload water consumption data, thereby accurately grasping the energy consumption of each dormitory room. At the second terminal (management end), the administrator issues a first setting command to set up an energy consumption cost gradient comparison table based on relevant regulations of the company or dormitory management, cost accounting, and energy market prices. When setting up the comparison table, the basic pricing unit for different energy types (e.g., price per kilowatt-hour of electricity, price per ton of water) is first determined. Then, different cost gradients are set according to the energy consumption tiers. For example, for electricity consumption, the cost might be set at 0.5 yuan per kilowatt-hour for monthly consumption between 0-50 kilowatt-hours; 0.6 yuan per kilowatt-hour for consumption between 51-100 kilowatt-hours; and 0.7 yuan per kilowatt-hour for consumption exceeding 100 kilowatt-hours. Similarly, a similar tiered pricing standard is set for water consumption, creating a complete energy consumption cost gradient table stored in the system. After obtaining the energy consumption of each dormitory room, the system calculates the corresponding energy cost for each room according to the pre-set energy consumption cost gradient table. Simultaneously, the system adds the calculated energy payment for each dormitory room to a pre-set unified billing statement. After employees complete the energy payment on their primary terminal, they send a payment completion command to the dormitory management system via the terminal. Upon receiving this command, the system searches for the corresponding energy payment in the pre-set billing statement and deletes it from the statement.

[0149] By setting up a tiered energy consumption cost comparison table, different fees are charged based on different energy consumption levels. Energy payment details are clearly added to the billing statement and sent to the primary terminal, allowing employees to clearly understand the energy consumption of their dormitory rooms and the corresponding cost details. The system automatically completes a series of operations, including energy consumption acquisition, cost calculation, bill generation, and updates, significantly improving the efficiency of financial management. Administrators no longer need to manually perform tedious energy cost calculations and billing work, saving substantial manpower and time costs.

[0150] It is understood that after step S610, the following steps may be included, but are not limited to:

[0151] Step S710: In response to a second setting command from the first terminal or the second terminal, set an energy consumption threshold;

[0152] Step S720: When the energy consumption is greater than or equal to the energy consumption threshold, send an energy consumption warning notification to the first terminal.

[0153] In steps S710 to S720, the system receives a second setting instruction from either the first terminal (employee terminal) or the second terminal (management terminal). This instruction contains specific setting information regarding energy consumption thresholds, such as an electricity consumption threshold of 100 kWh per month and a water consumption threshold of 10 tons per month, with separate settings for different energy types (electricity, water, etc.). After receiving the instruction, the system stores these energy consumption thresholds in the database. If a new second setting instruction is subsequently received, the system will promptly update the corresponding energy consumption thresholds to ensure that the latest settings are used.

[0154] When energy consumption exceeds or equals the energy consumption threshold, the system automatically generates an energy consumption warning notification. This notification may include information such as the dormitory room number, the type of energy exceeding the threshold, the current energy consumption, and possible energy-saving suggestions. Employees can receive the notification promptly on their terminal devices to understand that their dormitory room's energy consumption has exceeded the set standard. In this method, the energy consumption warning notification allows employees to be promptly aware that their dormitory room's energy consumption has reached or exceeded the threshold, thereby raising employees' awareness of energy usage and enabling them to reduce unnecessary use of electrical appliances, shorten appliance usage time, etc., effectively reducing energy waste and lowering energy costs.

[0155] It is understood that the control method of the employee dormitory management system provided in this application may also include, but is not limited to, the following steps:

[0156] Step S810: Obtain real-time temperature, humidity and light values ​​from multiple sources within the dormitory room;

[0157] Step S820: Based on multiple real-time temperature values, multiple real-time humidity values, and multiple real-time light sensitivity values, obtain the average temperature value, average humidity value, and average light sensitivity value;

[0158] Step S830: In response to a third setting command from the first terminal or the second terminal, set the temperature threshold range, humidity threshold range, and light sensing threshold range;

[0159] Step S840: When the average temperature value is outside the temperature threshold range, send a first control command to the electrical equipment in the corresponding dormitory room until the average temperature value is within the temperature threshold range, then send a first stop command to the electrical equipment in the corresponding dormitory room.

[0160] Step S850: When the average humidity value is outside the humidity threshold range, send a second control command to the electrical equipment in the corresponding dormitory room until the average humidity value is within the humidity threshold range, then send a second stop command to the electrical equipment in the corresponding dormitory room.

[0161] Step S860: When the average light sensitivity value is outside the light sensitivity threshold range, send a third control command to the electrical equipment in the corresponding dormitory room until the average light sensitivity value is within the light sensitivity threshold range, then send a third stop command to the electrical equipment in the corresponding dormitory room.

[0162] In steps S810 to S860, the system acquires multiple real-time temperature, humidity, and light values ​​for each dormitory room by installing multiple temperature sensors, humidity sensors, and light sensors in the rooms. These sensors continuously collect data at regular time intervals and transmit the collected data to the dormitory management system. The system calculates the average value for each of the acquired real-time temperature, humidity, and light values ​​for each dormitory room. Specifically, the maximum and minimum values ​​among the multiple real-time temperature values ​​within the same time period are removed, and the average of the remaining real-time temperature values ​​is calculated. Similarly, the calculation methods for the average humidity and average light values ​​are similar to those for the average temperature, and will not be repeated here. The system can receive a third setting command from a first terminal (employee terminal) or a second terminal (management terminal), which is used to set the temperature threshold range, humidity threshold range, and light threshold range. When the average temperature value of a dormitory room calculated by the system is outside the set temperature threshold range, a first control command is sent to the electrical equipment (such as air conditioners and electric heaters) in that dormitory room, depending on the specific situation. Similarly, when the average humidity in a dormitory room falls outside the set humidity threshold, the system sends a second control command to the relevant electrical appliances in that room (such as dehumidifiers and humidifiers). When the average light sensitivity in a dormitory room falls outside the set light sensitivity threshold, the system sends a third control command to the room's lights, motorized curtains, and other electrical appliances. By automatically adjusting the temperature, humidity, and light sensitivity of dormitory rooms, a more comfortable living environment can be provided for employees.

[0163] Maintaining temperature, humidity, and light within appropriate threshold ranges can prevent employees from feeling uncomfortable due to excessive heat, cold, humidity, dryness, or overly dim or bright lighting, thus improving their quality of life and satisfaction in the dormitory. Furthermore, the entire environmental control process is automated by the dormitory management system, eliminating the need for frequent manual checks of each room and manual adjustments to electrical appliances. Administrators only need to set appropriate threshold ranges to achieve intelligent management of the dormitory environment, significantly reducing the manpower burden and improving the efficiency of dormitory management.

[0164] Secondly, this application also provides an employee dormitory management system, including: at least one memory, at least one processor and at least one program, the program being stored in the memory, and the processor executing one or more programs to implement the control method of the employee dormitory management system described above.

[0165] In this system, the system first obtains the identity information of the employee awaiting check-in from a first terminal. This information is then sent to a second terminal, allowing administrators to approve the employee's check-in application and generate an approval result. If the approval is successful, the employee's identity information and the current dormitory status are input into a pre-defined deep feature matching model. The current dormitory status includes the bed information for each available bed. The deep feature matching model calculates the matching degree between the employee and each bed, taking into account relevant factors in the employee's identity information and the characteristics of the bed information. Based on this matching degree, the system analyzes and evaluates the compatibility between each bed and the employee, determining the most suitable bed number for that employee. After generating the bed number, the second terminal needs to confirm it. It can directly confirm the system-assigned bed number via a first operation command; if the assigned bed number is deemed inappropriate, it can be modified via the first operation command before resubmitting. Employees perform specific operations on a primary terminal. Upon receiving this instruction, the system recognizes that the employee has acknowledged and approved the assigned bed number, thus completing this information exchange process. In this application, the entire process, from obtaining the identity information of the employee awaiting admission and the approval process to bed matching and allocation, is automated. For example, information is rapidly transferred between the primary terminal (employee's end) and the secondary terminal (management end), eliminating the need for manual processing and transmission of numerous paper documents or data tables, significantly saving time and labor costs. Furthermore, utilizing a pre-set deep feature matching model, a comprehensive analysis of large amounts of employee and dormitory bed information can be performed quickly, rapidly generating a matching score and determining the bed number. Compared to the traditional method of manually evaluating and allocating beds one by one, this significantly improves allocation speed. Moreover, after the bed number information is generated, through the first operation instruction on the secondary terminal, managers can adjust the system allocation results according to the actual situation. By combining manual and system methods, the matching results can be further optimized based on the model allocation, adapting to special circumstances or specific management needs of the enterprise, improving the accuracy and flexibility of the matching.

[0166] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and signals, such as the program instructions / signals corresponding to the processing module in the embodiments of this application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and signals stored in the memory, thereby implementing the control method of the employee dormitory management system in the above method embodiments.

[0167] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data related to the control methods of the aforementioned employee dormitory management system. Furthermore, the memory may include high-speed random access memory and non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processing module via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0168] One or more signals are stored in memory, and when executed by one or more processors, the control method of the employee dormitory management system in any of the above method embodiments is executed.

[0169] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program that is executed by one or more processors, enabling the one or more processors to perform the control method of the employee dormitory management system described in the above method embodiments.

[0170] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] Based on the above description of the embodiments, those skilled in the art will understand that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable signals, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically contain computer-readable signals, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0172] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0173] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0174] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0176] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0177] The embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the above embodiments. Within the scope of knowledge possessed by those skilled in the art, various changes can be made without departing from the spirit of this application.

Claims

1. A control method of an employee dormitory management system, characterized by, The method comprises the following steps: obtaining the personal information of the employee to be checked in from the first terminal; sending the personal information to the second terminal and obtaining the approval result of the employee to be checked in from the second terminal; in response to the approval result, inputting the personal information and the current dormitory state into a preset deep feature matching model to obtain a first score value, a second score value and a third score value between the employee and each bed, respectively; wherein the current dormitory state comprises bed information corresponding to each bed; generating a matching degree between the employee and each bed according to the first score value, the second score value and the third score value; determining the bed number information of the employee according to the matching degree; in response to a first operation instruction from the second terminal, sending the bed number information to the first terminal, or updating the bed information and sending the updated bed information to the first terminal; in response to a second operation instruction from the first terminal, updating the current dormitory state; wherein the personal information comprises basic information, project participation information, work performance information and overtime regularity information, and the bed information comprises safety evaluation data of the corresponding area of each bed; inputting the personal information and the current dormitory state into a preset deep feature matching model to obtain a first score value between the employee and each bed, comprising: extracting the type basic information and the numerical basic information from the basic information; performing one-hot encoding and full connection layer processing on the type basic information to obtain a first basic feature vector; performing normalization and convolution processing on the numerical basic information to obtain a second basic feature vector; performing data combination and full connection layer processing on the project participation information to obtain a project feature vector; performing normalization and convolution processing on the work performance information to obtain a performance feature vector; performing periodic data integration on the overtime regularity information and inputting it into a preset time recurrent neural network to obtain an overtime feature vector; performing splicing processing on the first basic feature vector and the second basic feature vector to obtain a comprehensive basic feature vector, and performing splicing processing on the project feature vector, the performance feature vector and the overtime feature vector to obtain a comprehensive work feature vector; performing normalization and convolution processing on the safety evaluation data to obtain a safety feature vector; inputting the comprehensive basic feature vector, the comprehensive work feature vector and the safety feature vector into a preset first activation function to obtain the first score value between the employee and each bed.

2. The control method of the employee dormitory management system according to claim 1, characterized by, The personal information comprises personal interest information, personal social data information and personal living habit information, and the bed information comprises roommate identity information of employees corresponding to other occupied beds in the same dormitory room; wherein the roommate identity information comprises roommate interest information, roommate social data information and roommate living habit information; inputting the personal information and the current dormitory state into a preset deep feature matching model to obtain a second score value between the employee and each bed, comprising: inputting the self-interest hobby information, self-social data information and self-life habit information into a preset large language model to perform semantic feature extraction, to obtain a self-interest hobby feature vector, a self-social data feature vector and a self-life habit feature vector; inputting the roommate interest hobby information, roommate social data information and roommate life habit information into the large language model to perform semantic feature extraction, to obtain a roommate interest hobby feature vector, a roommate social data feature vector and a roommate life habit feature vector; performing similarity calculation processing on the self-interest hobby feature vector and the roommate interest hobby feature vector, the self-social data feature vector and the roommate social data feature vector, and the self-life habit feature vector and the roommate life habit feature vector, respectively, to obtain a first similarity, a second similarity and a third similarity; obtaining a second score value between the employee and each bed according to the first similarity, the second similarity and the third similarity.

3. The control method of the employee dormitory management system according to claim 1, characterized by, The self-identity information includes bed preference information and demand information, and the bed information includes position information corresponding to each bed and room information of a room in which the bed is located; inputting the self-identity information and the current dormitory state into a preset deep feature matching model to obtain a third score value between the employee and each bed, including: performing classification processing on the bed preference information to obtain a preference feature vector; performing one-hot encoding processing on the demand information, the position information and the room information, respectively, to obtain a demand feature vector, a position feature vector and a room feature vector; performing splicing processing on the preference feature vector and the demand feature vector to obtain a demand comprehensive feature vector; performing splicing processing on the position feature vector and the room feature vector to obtain a room comprehensive feature vector; inputting the demand comprehensive feature vector and the room comprehensive feature vector into a preset classifier model and performing decision processing to obtain the third score value between the employee and each bed.

4. The control method of the employee dormitory management system according to claim 1, characterized by, Further comprising: obtaining an energy consumption amount in the dormitory room; in response to a first setting instruction from the second terminal, setting an energy consumption fee gradient table; obtaining an energy payment matter according to the energy consumption amount and the energy consumption fee gradient table; adding the energy payment matter to a preset charge bill and sending it to the first terminal; in response to a payment completion instruction from the first terminal, deleting the energy payment matter corresponding to the payment completion instruction in the charge bill.

5. The control method of the employee dormitory management system according to claim 4, characterized by, After the step of obtaining the energy consumption amount in the dormitory room, further comprising: in response to a second setting instruction from the first terminal or the second terminal, setting an energy consumption threshold value; when the energy consumption amount is greater than or equal to the energy consumption threshold value, sending an energy consumption warning notification to the first terminal.

6. The control method of the employee dormitory management system according to claim 1, wherein Further comprising: obtaining a plurality of real-time temperature values, real-time humidity values and real-time light sensitivity values in the dormitory room; obtaining an average temperature value, an average humidity value and an average light sensitivity value according to a plurality of the real-time temperature values, a plurality of the real-time humidity values and a plurality of real-time light sensitivity values; setting a temperature threshold range, a humidity threshold range and a light threshold range in response to a third setting instruction from the first terminal or the second terminal; sending a first control instruction to the electrical equipment of the corresponding dormitory room when the average temperature value is outside the temperature threshold range, and sending a first stop instruction to the electrical equipment of the corresponding dormitory room when the average temperature value is within the temperature threshold range; sending a second control instruction to the electrical equipment of the corresponding dormitory room when the average humidity value is outside the humidity threshold range, and sending a second stop instruction to the electrical equipment of the corresponding dormitory room when the average humidity value is within the humidity threshold range; sending a third control instruction to the electrical equipment of the corresponding dormitory room when the average light value is outside the light threshold range, and sending a third stop instruction to the electrical equipment of the corresponding dormitory room when the average light value is within the light threshold range.

7. An employee dormitory management system characterized by comprising: comprising: at least one memory; at least one processor; at least one program; the program is stored in the memory, and the processor executes the at least one program to realize the control method of the employee dormitory management system according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, the computer readable storage medium stores computer executable signals for executing the control method of the employee dormitory management system according to any one of claims 1 to 6.

Images