Method, device and computer equipment for matching caregivers for disabled persons

Abstract

The present invention discloses a method, device and computer equipment for matching caregivers for disabled persons, which relates to the field of artificial intelligence, and is mainly capable of improving the matching accuracy of caregivers, thereby ensuring the quality of home care services. The method includes: obtaining basic disability information and historical care records corresponding to the disabled person; inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person; based on the nursing prescription corresponding to the disabled person, determining multiple target caregivers corresponding to the disabled person from a preset caregiver database; scoring the multiple target caregivers based on the historical care records, and determining a caregiver matching the disabled person from the multiple target caregivers according to the scoring results. The present invention relates to the field of artificial intelligence.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method, device and computer equipment for matching caregivers for disabled persons. Background Art

[0002] As my country's population aging is accelerating and becoming more and more advanced, especially when changes in social structure and family functions have led to the decline of the primary function of family care, the new home care model has become a good helper for caring for patients and elderly people at home. Home care has high requirements on the professional knowledge, practical ability and professional quality of visiting nurses. How to match suitable caregivers for patients and elderly people at home is of great significance to ensuring the quality of care and the development of the home care model.

[0003] At present, it is usually the management staff who selects suitable caregivers for home care services based on the disability information of patients or elderly people at home. However, this method of manually selecting caregivers is greatly influenced by the subjective factors of the management staff, and there is no guarantee that the selected caregivers are suitable for patients or elderly people at home, which will affect the quality of home care services. Summary of the invention

[0004] The present invention provides a method, an apparatus and a computer device for matching caregivers for disabled persons, which are mainly capable of improving the matching accuracy of caregivers, thereby ensuring the quality of home care services.

[0005] According to a first aspect of the present invention, there is provided a method for matching a caregiver for a disabled person, comprising:

[0006] Obtain basic disability information and historical care records corresponding to disabled persons;

[0007] Inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person;

[0008] Based on the nursing prescription corresponding to the disabled person, determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database;

[0009] The multiple target caregivers are scored based on the historical care records, and a caregiver matching the disabled person is determined from the multiple target caregivers according to the scoring results.

[0010] According to a second aspect of the present invention, there is provided a device for matching a caregiver for a disabled person, comprising:

[0011] An acquisition unit, used to acquire basic disability information and historical care records corresponding to disabled persons;

[0012] A prediction unit, used for inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtain a nursing prescription corresponding to the disabled person;

[0013] a determination unit, configured to determine a plurality of target caregivers corresponding to the disabled person from a preset caregiver database based on the nursing prescription corresponding to the disabled person;

[0014] A scoring unit is used to score the multiple target caregivers respectively based on the historical care records, and determine a caregiver who matches the disabled person from the multiple target caregivers according to the scoring results.

[0015] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0016] Obtain basic disability information and historical care records corresponding to disabled persons;

[0017] Inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person;

[0018] Based on the nursing prescription corresponding to the disabled person, determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database;

[0019] The multiple target caregivers are scored based on the historical care records, and a caregiver matching the disabled person is determined from the multiple target caregivers according to the scoring results.

[0020] According to a fourth aspect of the present invention, there is provided a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the following steps are implemented:

[0021] Obtain basic disability information and historical care records corresponding to disabled persons;

[0022] Inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person;

[0023] Based on the nursing prescription corresponding to the disabled person, determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database;

[0024] The multiple target caregivers are scored respectively based on the historical care records, and a caregiver matching the disabled person is determined from the multiple target caregivers according to the scoring results.

[0025] According to a method, device and computer equipment for matching caregivers for disabled persons provided by the present invention, compared with the current way in which managers select caregivers for patients or elderly people at home based on their disability information, the present invention obtains basic disability information and historical care records corresponding to the disabled person; and inputs the basic disability information into a preset nursing prescription prediction model for prescription prediction to obtain a nursing prescription corresponding to the disabled person; at the same time, based on the nursing prescription corresponding to the disabled person, multiple target caregivers corresponding to the disabled person are determined from a preset caregiver database; finally, the multiple target caregivers are scored based on the historical care records, and caregivers matching the disabled person are determined from the multiple target caregivers according to the scoring results, thereby selecting multiple target caregivers from the preset caregiver database and scoring the target caregivers, so that caregivers matching the disabled person can be determined, thereby automatically matching suitable caregivers for the disabled person, improving the matching accuracy of caregivers, and further ensuring the quality of home care services. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 A flow chart of a method for matching caregivers for disabled persons provided by an embodiment of the present invention is shown;

[0028] Figure 2 Another method flow chart for matching caregivers for disabled persons provided by an embodiment of the present invention is shown;

[0029] Figure 3 A schematic diagram of the structure of a device for matching caregivers for disabled persons provided by an embodiment of the present invention is shown;

[0030] Figure 4 A schematic diagram of the structure of another device for matching caregivers for disabled persons provided by an embodiment of the present invention is shown;

[0031] Figure 5 A schematic diagram of the physical structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] The present invention will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0033] At present, the way managers select suitable caregivers for patients or elderly people at home based on their disability information is greatly influenced by their subjective factors. There is no guarantee that the selected caregivers are suitable for patients or elderly people at home, which will affect the quality of home care services.

[0034] In order to solve the above problems, the embodiment of the present invention provides a method for matching caregivers for disabled persons, such as Figure 1 As shown, the method includes:

[0035] 101. Obtain basic disability information and historical care records corresponding to disabled persons.

[0036] Among them, disabled persons refer to patients or elderly people at home who need care. The basic disability information corresponding to disabled persons includes the name, age, gender, disability level, physical activity status, hospital diagnosis information, current medication information, current treatment information, etc. The historical care records include the information of caregivers who have previously served the disabled persons. The caregiver information specifically includes the caregiver's name, gender, care score, personality test score, skill assessment score, etc.

[0037] For the embodiments of the present invention, in order to overcome the defect in the prior art that it is impossible to match suitable caregivers for disabled persons, thereby affecting the quality of home care services, the embodiments of the present invention can predict the nursing prescriptions corresponding to disabled persons through the basic disability information of disabled persons and the preset nursing prescription prediction model, so that multiple target caregivers can be selected from the preset caregiver library. At the same time, by scoring multiple target caregivers, caregivers matching the disabled persons can be determined and recommended to provide care for the disabled persons, thereby improving the matching accuracy of caregivers and ensuring the quality of home care services. The embodiments of the present invention are mainly used in the scenario of matching caregivers for disabled persons. The execution subject of the embodiments of the present invention is a device or equipment that can match caregivers for disabled persons, which can be specifically set on the client or server side.

[0038] Specifically, disabled persons who need care services will register in the system in advance and fill in the basic information of the disabled persons, including name, age, ID number, disability level, physical activity status, medical diagnosis information, current service drugs or treatments received, etc. If the disabled person passes the basic information review, the registration will be successful, and the disabled person can subsequently apply for care services online. The above information of the disabled person will be stored in the disabled person information database of the system. At the same time, the system will also record the historical care records of the disabled person after each care service. When the disabled person applies for care services online, the system will receive the disabled person's care service request, which will carry the disabled person's identity ID and current location information. Based on the disabled person's identity ID, the system can call the basic disability information and historical care records corresponding to the disabled person from the disabled person information database, so as to match the caregiver for this care service according to the basic disability information and historical care records.

[0039] 102. Input the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtain a nursing prescription corresponding to the disabled person.

[0040] Among them, nursing prescriptions include basic cleaning care, cleaning care + medical care, cleaning care + spiritual comfort, cleaning care + medical care + spiritual comfort, etc. Multiple nursing prescriptions can be generated according to actual business needs.

[0041] For the embodiments of the present invention, in order to improve the accuracy of the preset nursing prescription prediction model, before using the preset nursing prescription prediction model to predict the basic disability information, it is necessary to collect the basic disability information and the corresponding nursing prescriptions corresponding to the historical disabled persons in advance, and use them as sample data, use the sample data to train the initial nursing prescription prediction model, and construct a preset nursing prescription prediction model. When it is necessary to obtain the nursing prescription corresponding to the disabled person, the basic disability information corresponding to the disabled person is input into the constructed preset nursing prescription prediction model for prescription prediction, and the nursing prescription corresponding to the disabled person is obtained, so that according to the nursing prescription, multiple target caregivers can be determined, and according to the historical care records, the caregivers who match the disabled person can be determined from the multiple target caregivers, so that suitable caregivers can be matched for the disabled person, thereby improving the quality of home care services.

[0042] 103. Based on the nursing prescription corresponding to the disabled person, determine multiple target caregivers corresponding to the disabled person from a preset caregiver database.

[0043] Among them, the preset caregiver database stores a large number of caregivers of various care levels and the basic information of each caregiver, which includes the caregiver's name, gender, age, address, personality assessment results, theoretical knowledge assessment results, skill assessment results, care level and other contents.

[0044] For the embodiment of the present invention, after obtaining the nursing prescription corresponding to the disabled person, it is necessary to determine the corresponding care level according to the nursing prescription, wherein different nursing prescriptions correspond to different care levels. After determining the corresponding care level according to the nursing prescription corresponding to the disabled person, all target caregivers with the care level are screened out in the preset caregiver database, and all the screened out target caregivers are the multiple target caregivers corresponding to the disabled person. It should be noted that the final multiple target caregivers can also be determined according to other needs of the disabled person. For example, if the disabled person needs a female caregiver, the target caregiver must not only meet the requirements of the care level, but also meet the gender requirements. Thus, the care level required by the disabled person is determined through the predicted nursing prescription, and multiple target caregivers are screened out according to the care level. Finally, a caregiver matching the disabled person is determined from the target caregivers, so that the disabled person can be matched with a suitable caregiver, thereby improving the quality of home care services.

[0045] 104. Score the multiple target caregivers respectively based on the historical care records, and determine a caregiver who matches the disabled person from among the multiple target caregivers according to the scoring results.

[0046] For the embodiment of the present invention, since a care score is given to the caregiver after each care service is provided to a disabled person, and the care score is stored in the historical care record, historical caregivers with higher care scores can be screened according to the historical care records of the disabled person, and the basic care information of the historical caregivers with higher care scores can be analyzed. According to the analysis results, the scoring dimension is determined. At the same time, based on the scoring dimension, multiple target caregivers are scored, and finally the target caregiver corresponding to the highest score is determined as the caregiver who matches the disabled person.

[0047] Furthermore, after determining the caregiver who matches the disabled person, the system will assign the care task to the caregiver. After the caregiver agrees to accept the task, the system will obtain the caregiver's current location information and plan an optimal route for the caregiver based on the caregiver's current location information and the disabled person's location information. If the caregiver deviates from the optimal route during the journey, the system will send an alarm message to the manager's terminal. At the same time, while planning the optimal route for the caregiver, the system will also estimate the estimated time for the caregiver to reach the disabled person's location based on the optimal route. If the caregiver's clock-in time is far from the estimated time, the system will also send an alarm message to the manager's terminal. In addition, after the caregiver arrives at the destination, the system can obtain the caregiver's location information in real time. If the caregiver deviates from the established location information for a long time, or has no physical location information for a long time, the system will also send an alarm message to the manager's terminal. Therefore, by determining multiple target caregivers and scoring them according to the historical care records of the disabled person, the caregiver with the highest score is finally selected to care for the disabled person. This avoids the influence of subjective factors when manually selecting caregivers, and the inability to guarantee that the selected caregiver is suitable for the disabled person, thereby improving the matching accuracy of the caregivers. At the same time, after the caregiver who matches the disabled person receives the care task, the caregiver's location information can be monitored in real time, so as to achieve control over the caregiver and ensure the quality of care services.

[0048] According to a method for matching caregivers for disabled persons provided by the present invention, compared with the current way in which management personnel select caregivers for patients or elderly people at home based on their disability information, the present invention obtains basic disability information and historical care records corresponding to the disabled person; and inputs the basic disability information into a preset nursing prescription prediction model for prescription prediction to obtain a nursing prescription corresponding to the disabled person; at the same time, based on the nursing prescription corresponding to the disabled person, multiple target caregivers corresponding to the disabled person are determined from a preset caregiver database; finally, the multiple target caregivers are scored based on the historical care records, and caregivers matching the disabled person are determined from the multiple target caregivers according to the scoring results, thereby selecting multiple target caregivers from the preset caregiver database and scoring the target caregivers, so that caregivers matching the disabled person can be determined, thereby automatically matching suitable caregivers for the disabled person, improving the matching accuracy of caregivers, and further ensuring the quality of home care services.

[0049] Further, in order to better illustrate the above process of matching caregivers for disabled persons, as a refinement and extension of the above embodiment, the embodiment of the present invention provides another method for matching caregivers for disabled persons, such as Figure 2 As shown, the method includes:

[0050] 201. Obtain basic disability information and historical care records corresponding to disabled persons.

[0051] For the embodiment of the present invention, if the disabled person applies for care services for the first time, he / she needs to register in the system in advance and fill in the basic information of the disabled person, wherein the basic information includes basic disability information and identity information, etc., so as to facilitate the subsequent online application for care services. If the disabled person is not applying for care services for the first time, the basic disability information corresponding to the disabled person is stored in the disabled person information database of the system. At the same time, the system also stores the historical care records corresponding to the disabled person. When the disabled person applies for care services online, the system will automatically call out the basic disability information and historical care records corresponding to the disabled person according to the identity ID of the disabled person.

[0052] 202. Input the basic disability information into the preset multi-layer perceptron to perform prescription prediction, and obtain the probability value of the disabled person requiring different nursing prescriptions.

[0053] Among them, the preset multi-layer perceptron is a neural network model, which includes an input layer, a hidden layer and an output layer.

[0054] For the embodiment of the present invention, in order to improve the accuracy of obtaining nursing prescriptions, it is necessary to input the basic disability information corresponding to the disabled person into the hidden layer through the input layer of the preset multi-layer perceptron, and the result output by the hidden layer is:

[0055] f(W1x+b1)

[0056] Among them, x is the basic disability information corresponding to the disabled person, W1 is the weight of the hidden layer, which is also the connection coefficient of the preset multi-layer perceptron, b1 is the bias coefficient of the hidden layer, and the f function can usually use the sigmoid function or the tanh function, as shown below:

[0057] sigmoid(x)=1 / (1+e -x )

[0058] tanh(x)=(e x -e -x ) / (e 1 +e -x )

[0059] Among them, the basic disability information corresponding to the disabled person is input into the hidden layer through the input layer of the preset multi-layer perceptron. After the output result of the hidden layer is obtained, the result is input into the output layer, that is, the softmax layer of the preset multi-layer perceptron. The nursing prescription is predicted through the output layer, and the prediction result obtained is:

[0060] softmax(W2f(W1x+b1)+b2)

[0061] Among them, W2 is the weight coefficient of the output layer, b2 is the bias coefficient of the output layer, and the output layer of the multilayer perceptron can output the probability value of different nursing prescriptions corresponding to disabled persons, and determine the corresponding nursing prescriptions for disabled persons based on the probability value.

[0062] 203. Determine the nursing prescription corresponding to the maximum probability value according to the probability value that the disabled person needs different nursing prescriptions, and determine the nursing prescription corresponding to the maximum probability value as the nursing prescription corresponding to the disabled person.

[0063] Corresponding to the embodiment of the present invention, after the basic disability information corresponding to the disabled person is input into the preset multi-layer perceptron for prediction and the probability values ​​of different nursing prescriptions are obtained, it is necessary to determine the nursing prescription corresponding to the maximum probability value. The nursing prescription corresponding to the maximum probability value is the nursing prescription that the predicted disabled person finally corresponds to, so that according to the nursing prescription, multiple target caregivers can be determined in the preset caregiver database, and finally a caregiver who matches the disabled person can be selected from the multiple target caregivers.

[0064] 204. Based on the nursing prescription corresponding to the disabled person, determine multiple target caregivers corresponding to the disabled person from a preset caregiver database.

[0065] For the embodiment of the present invention, in order to ensure that a large number of caregivers of various care levels are stored in the preset caregiver database, before determining multiple target caregivers corresponding to the disabled person from the preset caregiver database according to the nursing prescription corresponding to the disabled person, the method also includes: obtaining the personality test score, theoretical knowledge score and skill test score corresponding to each caregiver; inputting the personality test score, the theoretical knowledge score and the skill test score into the preset level prediction model for level prediction, so as to obtain the care level corresponding to each caregiver.

[0066] Among them, the personality test scores, theoretical knowledge scores and skill test scores corresponding to each caregiver are the corresponding scores obtained by conducting personality tests, theoretical knowledge tests and skill tests on each caregiver in advance. The preset grade prediction model can specifically be a preset regression grade prediction model.

[0067] For the embodiment of the present invention, in order to obtain the care level corresponding to each caregiver, it is first necessary to conduct personality tests, theoretical knowledge tests and skill tests on each caregiver respectively, and obtain the personality test scores, theoretical knowledge scores and skill test scores corresponding to the caregivers respectively. Then, the personality test scores, theoretical knowledge scores and skill test scores corresponding to the caregivers are input together into a preset regression grade prediction model for grade prediction. The specific prediction process of the preset regression grade prediction model is: determining the weight coefficients of the personality test scores, the theoretical knowledge scores and the skill test scores in the preset regression grade prediction model respectively; based on the weight coefficients, performing weighted summation of the personality test scores, the theoretical knowledge scores and the skill test scores to obtain the first total scores corresponding to each caregiver; based on the first total score, determining the care level corresponding to each caregiver.

[0068] Furthermore, because each care level corresponds to an assessment total score range, based on the first total score corresponding to the caregiver, it is determined to which assessment total score range the first total score specifically belongs, and then the care level corresponding to the caregiver can be determined according to the care level corresponding to the assessment total score range. For example, the first-level care level corresponds to a total assessment score range of 90-100 points, the second-level care level corresponds to a total assessment score range of 80-90 points, the third-level care level corresponds to a total assessment score range of 70-80 points, the fourth-level care level corresponds to a total assessment score range of 60-70 points, and the fifth-level care level corresponds to a total assessment score range of 50-60 points. If the first total score corresponding to the caregiver is 85 points, which is within the range of 80-90 points, it can be determined that the caregiver corresponds to the second-level care level. Therefore, according to the first total score corresponding to each caregiver, the care level corresponding to each caregiver can be determined, and the care levels corresponding to all caregivers are recorded in the preset caregiver database.

[0069] Furthermore, after recording the care levels corresponding to all caregivers into a preset caregiver database, in order to determine multiple target caregivers corresponding to the disabled person from the preset caregiver database according to the nursing prescription corresponding to the disabled person, step 204 specifically includes: querying the preset care level list according to the nursing prescription corresponding to the disabled person, and determining the care level required for the disabled person, wherein the preset care level list records the care levels corresponding to different nursing prescriptions; and screening multiple target caregivers with the care level from the preset caregiver database, wherein the preset caregiver database records caregivers with different care levels.

[0070] For the embodiment of the present invention, in order to screen out multiple target caregivers corresponding to disabled persons in the preset nursing staff database, it is first necessary to query the preset care level list according to the nursing prescription corresponding to the disabled person, determine the care level corresponding to the nursing prescription, and determine the care level as the care level required by the disabled person, and according to the care level, screen out multiple target caregivers with the care level in the preset nursing staff database, wherein different nursing prescriptions correspond to different care levels, if the disabled person only needs cleaning care, it corresponds to the fifth level of care level, that is, the disabled person only needs the care of a junior worker; if the disabled person needs cleaning care + spiritual comfort, it corresponds to the fourth level of care level, that is, the disabled person needs the care of an intermediate worker; if the disabled person needs cleaning care + medical care, it corresponds to the third level of care level, that is, the disabled person The disabled person needs care from a senior worker; if the disabled person needs medical care + spiritual comfort, it corresponds to the second-level care level, that is, the disabled person needs care from a technician; if the disabled person needs cleaning care + medical care + spiritual comfort, it corresponds to the first-level care level, that is, the disabled person needs care from a senior technician. Therefore, through the nursing prescription corresponding to the disabled person, the care level he needs can be determined, and then according to the care level, multiple target caregivers with this care level are screened out from the preset caregiver library. For example, it is predicted that the nursing prescription corresponding to the disabled person includes cleaning care, medical care and spiritual comfort. According to the nursing prescription, it is determined that the disabled person needs a caregiver with a first-level care level, and all caregivers with a first-level care level are screened out from the preset caregiver library and used as the multiple target caregivers corresponding to the disabled person.

[0071] 205. Score the multiple target caregivers respectively based on the historical care records, and determine a caregiver who matches the disabled person from among the multiple target caregivers according to the scoring results.

[0072] For the embodiment of the present invention, after determining multiple target caregivers corresponding to the disabled person, it is necessary to determine a caregiver matching the disabled person from the multiple target caregivers. Based on this, step 205 specifically includes: based on the historical care records corresponding to the disabled person, screening out historical caregivers whose care scores are greater than preset scores; obtaining the personality test results and skill assessment results in the basic care information of the historical caregivers, if the personality assessment results and the skill assessment results both meet the preset assessment result requirements, then using the personality assessment and the skill assessment as the scoring dimensions corresponding to the multiple target caregivers; determining the scoring weights corresponding to the scoring dimensions, and the scores of the multiple target caregivers under the scoring dimensions respectively; based on the scoring weights, performing weighted summation on the scores under the scoring dimensions to obtain the second total scores corresponding to the multiple target caregivers respectively; based on the second total scores corresponding to the multiple target caregivers respectively, determining the target caregiver with the highest second total score, and determining the target caregiver with the highest second total score as the caregiver matching the disabled person.

[0073] Among them, the historical caregivers are caregivers who have served the disabled persons before. Specifically, after obtaining the historical care records of the disabled persons and determining the multiple target caregivers corresponding to the disabled persons, it is necessary to screen out the historical caregivers whose care scores are greater than the preset scores according to the historical caregivers recorded in the historical care records and the corresponding care scores, and analyze the care information such as the personality test scores, skill scores and distance from the disabled persons corresponding to the historical caregivers. The main analysis is which type of caregiver the disabled persons prefer, and then determine the scoring dimensions corresponding to the multiple target caregivers and the scores of the multiple target caregivers under the scoring dimensions respectively, and determine the second total scores corresponding to the multiple target caregivers respectively based on the scoring weights corresponding to the scoring dimensions, and finally screen out the highest second total score from the second total score. The target caregiver corresponding to the highest second total score is the caregiver who matches the disabled persons.

[0074] For example, according to the historical care records of disabled persons, there are three historical caregivers with care scores higher than 80 points. By analyzing the basic information of these three historical caregivers, it can be found that the personality assessment results of these three historical caregivers are all greater than 80 points. This shows that the disabled person is more inclined to caregivers with better personalities, and personality can be used as a scoring dimension to score multiple target caregivers. For another example, through analysis, it is found that the skill assessment results of the three historical caregivers are all greater than 80 points. This shows that the disabled person is more inclined to caregivers with higher skills, and skills can be used as a scoring dimension to score multiple target caregivers.

[0075] Furthermore, the distance between the caregiver and the disabled person can also be used as a scoring dimension to select a more matching caregiver for the disabled person. For example, multiple target caregivers are finally scored from the two dimensions of distance and personality. The distance score corresponding to each target caregiver is determined according to the distance between each target caregiver and the disabled person. The closer the distance, the higher the distance score. Then, based on the weights corresponding to the determined distance and personality, the distance score and the personality assessment value are weighted and summed to obtain the second total score corresponding to each target caregiver. The higher the second total score, the higher the match between the target caregiver and the disabled person. Therefore, based on the scoring results corresponding to each target caregiver, a caregiver with the highest second total score is selected and determined as the caregiver who matches the disabled person.

[0076] Furthermore, after determining the caregiver who matches the disabled person, the caregiver accepts the care task and provides care services to the disabled person. The method also includes: obtaining voice information of the caregiver who matches the disabled person during the care service process, and the service score given by the disabled person for the care service; converting the voice information into text information, and performing word segmentation processing on the text information to obtain each word segmentation corresponding to the text information; matching each word segmentation with each keyword in a preset keyword library to determine the keywords contained in each word segmentation; determining the score corresponding to the keyword, and calculating the care score of the care service provided by the caregiver who matches the disabled person based on the score corresponding to the keyword and the service score given by the disabled person.

[0077] Among them, the preset keyword library contains a large number of keywords used for evaluation, such as awesome, just right, great, average, not good, etc.

[0078] For the embodiment of the present invention, during the entire care service process, the system can obtain voice information of the disabled person and the caregiver by calling the mobile recording device, and convert the voice information into text information, then perform word segmentation processing on the text information to obtain each word contained in the text information, match each word with each keyword in the preset keyword library, and determine the keyword in the preset keyword library that matches any word in each word. For example, the voice information converted into text is "Your personality is really good", the text information is segmented to obtain each word as "You / your / personality / is / really good", and the corresponding word of the text information is matched. Each segmented word is matched with each keyword in the preset keyword library, and it is found that the keyword "really good" exists in each segmented word corresponding to the text information. Since different keywords correspond to different scores, such as "really good, really good" corresponds to 10 points, "average" corresponds to 5 points, and "not good" corresponds to 2 points, the score corresponding to the keyword can be determined. At the same time, after the care service is completed, the disabled person or his family will also give a service score, and the score weights corresponding to the keyword score and the service score are determined respectively. Based on the score weight, the service score and the score corresponding to the keyword are weighted and summed to obtain the care score corresponding to the care service provided by the caregiver.

[0079] According to another method for matching caregivers for disabled persons provided by the present invention, compared with the current way in which management personnel select caregivers for patients or elderly people at home based on their disability information, the present invention obtains basic disability information and historical care records corresponding to the disabled person; and inputs the basic disability information into a preset nursing prescription prediction model for prescription prediction to obtain a nursing prescription corresponding to the disabled person; at the same time, based on the nursing prescription corresponding to the disabled person, multiple target caregivers corresponding to the disabled person are determined from a preset caregiver database; finally, the multiple target caregivers are scored based on the historical care records, and according to the scoring results, caregivers matching the disabled person are determined from the multiple target caregivers, thereby selecting multiple target caregivers from the preset caregiver database and scoring the target caregivers, so that caregivers matching the disabled person can be determined, thereby automatically matching suitable caregivers for the disabled person, improving the matching accuracy of caregivers, and further ensuring the quality of home care services.

[0080] Further, as Figure 1 In a specific implementation, an embodiment of the present invention provides a device for matching caregivers for disabled persons, such as Figure 3 As shown, the device includes: an acquisition unit 31, a prediction unit 32, a determination unit 33 and a scoring unit 34.

[0081] The acquisition unit 31 may be used to acquire basic disability information and historical care records corresponding to the disabled person.

[0082] The prediction unit 32 may be used to input the basic disability information into a preset nursing prescription prediction model to perform prescription prediction and obtain a nursing prescription corresponding to the disabled person.

[0083] The determining unit 33 may be configured to determine a plurality of target caregivers corresponding to the disabled person from a preset caregiver database based on the nursing prescription corresponding to the disabled person.

[0084] The scoring unit 34 may be configured to score the multiple target caregivers respectively based on the historical care records, and determine a caregiver matching the disabled person from among the multiple target caregivers according to the scoring results.

[0085] In specific application scenarios, in order to obtain the corresponding nursing prescriptions for disabled persons, such as Figure 4 As shown, the prediction unit 32 includes a prediction module 321 and a first determination module 322 .

[0086] The prediction module 321 can be used to input the basic disability information into the preset multi-layer perceptron to perform prescription prediction, and obtain the probability value of the disabled person requiring different nursing prescriptions.

[0087] The first determination module 322 can be used to determine the nursing prescription corresponding to the maximum probability value according to the probability value that the disabled person needs different nursing prescriptions, and determine the nursing prescription corresponding to the maximum probability value as the nursing prescription corresponding to the disabled person.

[0088] In a specific application scenario, in order to determine multiple target caregivers corresponding to the disabled person, the determination unit 33 includes a second determination module 331 and a first screening module 332 .

[0089] The second determination module 331 can be used to query a preset care level list according to the nursing prescription corresponding to the disabled person, and determine the care level required by the disabled person, wherein the preset care level list records the care levels corresponding to different nursing prescriptions.

[0090] The first screening module 332 may be used to screen a plurality of target caregivers having the care level from the preset caregiver database, wherein the preset caregiver database records caregivers of different care levels.

[0091] In a specific application scenario, in order to determine the care level corresponding to each caregiver, before selecting multiple target caregivers of corresponding care levels from a preset caregiver database, the determination unit 33 also includes an acquisition module 333 and a level prediction module 334.

[0092] The acquisition module 333 may be used to acquire the personality test score, theoretical knowledge score and skill test score corresponding to each caregiver.

[0093] The level prediction module 334 can be used to input the personality test score, the theoretical knowledge score and the skill test score into a preset level prediction model to perform level prediction and obtain the care level corresponding to each caregiver.

[0094] In a specific application scenario, in order to determine the care level of each caregiver, the level prediction module 334 includes a determination submodule and a summation submodule.

[0095] The determination submodule may be used to determine the weight coefficients of the personality test score, the theoretical knowledge score and the skill test score in the preset regression grade prediction model respectively.

[0096] The summing submodule may be used to perform weighted summation of the personality test score, the theoretical knowledge score and the skill test score based on the weight coefficient to obtain a first total score corresponding to each caregiver.

[0097] The determination submodule can be specifically used to determine the care level corresponding to each caregiver based on the first total score.

[0098] In a specific application scenario, in order to determine a caregiver who matches the disabled person from a plurality of target caregivers, the scoring unit 34 includes a second screening module 341 , an analysis module 342 , a third determination module 343 and a summation module 344 .

[0099] The second screening module 341 may be used to screen out historical caregivers whose care scores are greater than a preset score based on the historical care records corresponding to the disabled person.

[0100] The analysis module 342 can be used to obtain the personality test results and skill assessment results in the basic care information of the historical caregivers. If the personality assessment results and the skill assessment results both meet the preset assessment result requirements, the personality assessment and skill assessment will be used as the scoring dimensions corresponding to the multiple target caregivers.

[0101] The third determination module 343 may be used to determine the scoring weights corresponding to the scoring dimensions and the scores of the multiple target caregivers under the scoring dimensions respectively.

[0102] The summing module 344 may be configured to perform weighted summation of the scores under the scoring dimensions based on the scoring weights to obtain second total scores corresponding to the multiple target caregivers respectively.

[0103] The third determination module 343 can be specifically used to determine the target caregiver with the highest second total score based on the second total scores corresponding to the multiple target caregivers, and determine the target caregiver with the highest second total score as the caregiver who matches the disabled person.

[0104] In a specific application scenario, after a matching caregiver is determined for a disabled person, in order to score the caregiver's care during this care service, the device further includes a word segmentation unit 35 , a matching unit 36 ​​and a calculation unit 37 .

[0105] The acquisition unit 31 may also be used to acquire voice information of a caregiver matching the disabled person during the care service, and a service score given by the disabled person for the care service.

[0106] The word segmentation unit 35 may be used to convert the voice information into text information, and perform word segmentation processing on the text information to obtain each word segment corresponding to the text information.

[0107] The matching unit 36 ​​may be configured to match each of the segmented words with each of the keywords in a preset keyword library to determine the keywords included in each of the segmented words.

[0108] The calculation unit 37 can be used to determine the score corresponding to the keyword, and calculate the care score of the care service provided by the caregiver matching the disabled person based on the score corresponding to the keyword and the service score given by the disabled person.

[0109] It should be noted that for other corresponding descriptions of the functional modules involved in the device for matching caregivers for disabled persons provided in an embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0110] Based on the above Figure 1The method shown, accordingly, an embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented: obtaining basic disability information and historical care records corresponding to the disabled person; inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person; based on the nursing prescription corresponding to the disabled person, determining multiple target caregivers corresponding to the disabled person from a preset caregiver database; scoring the multiple target caregivers respectively based on the historical care records, and determining a caregiver matching the disabled person from the multiple target caregivers according to the scoring results.

[0111] Based on the above Figure 1 The method shown and Figure 3 The embodiment of the device shown in the figure, the embodiment of the present invention also provides a physical structure diagram of a computer device, such as Figure 5 As shown, the computer device includes: a processor 41, a memory 42, and a computer program stored in the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and the processor 41 implements the following steps when executing the program: obtaining basic disability information and historical care records corresponding to the disabled person; inputting the basic disability information into a preset nursing prescription prediction model for prescription prediction to obtain a nursing prescription corresponding to the disabled person; based on the nursing prescription corresponding to the disabled person, determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database; scoring the plurality of target caregivers respectively based on the historical care records, and determining a caregiver matching the disabled person from the plurality of target caregivers according to the scoring results.

[0112] Through the technical solution of the present invention, the present invention obtains basic disability information and historical care records corresponding to the disabled person; and inputs the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, thereby obtaining a nursing prescription corresponding to the disabled person; at the same time, based on the nursing prescription corresponding to the disabled person, multiple target caregivers corresponding to the disabled person are determined from a preset caregiver database; finally, the multiple target caregivers are scored based on the historical care records, and according to the scoring results, caregivers matching the disabled person are determined from the multiple target caregivers, thereby selecting multiple target caregivers from the preset caregiver database and scoring the target caregivers, so that caregivers matching the disabled person can be determined, thereby automatically matching suitable caregivers for the disabled person, improving the matching accuracy of caregivers, and further ensuring the quality of home care services.

[0113] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for matching caregivers for disabled persons, characterized in that: include: Obtaining basic disability information and historical care records corresponding to the disabled person, wherein the basic disability information includes the name, age, gender, disability level, physical activity status, hospital diagnosis information, current medication information, and current treatment information of the disabled person, and the historical care records include information on caregivers who have served the disabled person, and the caregiver information includes the name, gender, care score, personality test score, and skill assessment score of the caregiver; Inputting the basic disability information into a preset nursing prescription prediction model for prescription prediction, and obtaining a nursing prescription corresponding to the disabled person, wherein the nursing prescription includes basic cleaning care, cleaning care + medical care, cleaning care + spiritual comfort, and cleaning care + medical care + spiritual comfort; Based on the nursing prescription corresponding to the disabled person, determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database; Scoring the multiple target caregivers respectively based on the historical care records, and determining a caregiver matching the disabled person from the multiple target caregivers according to the scoring results, including: screening out historical caregivers whose care scores are greater than preset scores according to the historical care records corresponding to the disabled person, obtaining personality assessment results and skill assessment results in the basic care information of the historical caregivers, and if both the personality assessment results and the skill assessment results meet the preset assessment result requirements, using the personality assessment and the skill assessment as the scoring dimensions corresponding to the multiple target caregivers, determining the scoring weights corresponding to the scoring dimensions, and the scores of the multiple target caregivers respectively under the scoring dimensions, and performing weighted summation of the scores under the scoring dimensions based on the scoring weights to obtain second total scores corresponding to the multiple target caregivers respectively, determining the target caregiver with the highest second total score based on the second total scores corresponding to the multiple target caregivers respectively, and determining the target caregiver with the highest second total score as the caregiver matching the disabled person; The preset nursing prescription prediction model is a preset multi-layer perceptron, and the basic disability information is input into the preset nursing prescription prediction model for prescription prediction to obtain the nursing prescription corresponding to the disabled person, including: Inputting the basic disability information into the preset multi-layer perceptron to perform prescription prediction, and obtaining the probability value of the disabled person needing different nursing prescriptions; According to the probability value that the disabled person needs different nursing prescriptions, the nursing prescription corresponding to the maximum probability value is determined, and the nursing prescription corresponding to the maximum probability value is determined as the nursing prescription corresponding to the disabled person.

2. The method according to claim 1, characterized in that The step of determining a plurality of target caregivers corresponding to the disabled person from a preset caregiver database based on the care prescription corresponding to the disabled person includes: According to the nursing prescription corresponding to the disabled person, a preset care level list is searched to determine the care level required by the disabled person, wherein the preset care level list records the care levels corresponding to different nursing prescriptions; A plurality of target caregivers having the care level are screened from the preset caregiver database, wherein caregivers of different care levels are recorded in the preset caregiver database.

3. The method according to claim 2, characterized in that Before screening a plurality of target caregivers with the care level from the preset caregiver database, the method further includes: Obtain the personality test scores, theoretical knowledge scores and skill test scores corresponding to each caregiver; The personality test score, the theoretical knowledge score and the skill test score are input together into a preset grade prediction model for grade prediction to obtain the care grade corresponding to each caregiver.

4. The method according to claim 3, characterized in that The preset grade prediction model is a preset regression grade prediction model, and the personality test score, the theoretical knowledge score and the skill test score are input into the preset grade prediction model together for grade prediction to obtain the care grade corresponding to each caregiver, including: Determine the weight coefficients of the personality test score, the theoretical knowledge score and the skill test score in the preset regression grade prediction model respectively; Based on the weight coefficient, weighted summing the personality test score, the theoretical knowledge score and the skill test score is performed to obtain a first total score corresponding to each caregiver; Based on the first total score, the care level corresponding to each caregiver is determined.

5. The method according to claim 1, characterized in that After scoring the multiple target caregivers respectively based on the historical care records and determining a caregiver matching the disabled person from the multiple target caregivers according to the scoring results, the method further includes: Obtaining the voice information of the caregiver matched with the disabled person during the care service, as well as the service rating given by the disabled person for the care service; Convert the voice information into text information, and perform word segmentation processing on the text information to obtain each word segment corresponding to the text information; Matching each of the segmented words with each of the keywords in a preset keyword library to determine the keywords contained in each of the segmented words; Determine the score corresponding to the keyword, and based on the score corresponding to the keyword and the service score given by the disabled person, calculate the care score of the care service provided by the caregiver who matches the disabled person.

6. A device for matching caregivers for disabled persons, characterized in that: include: an acquisition unit, used to acquire basic disability information and historical care records corresponding to the disabled person, wherein the basic disability information includes the name, age, gender, disability level, physical activity status, hospital diagnosis information, current medication information, and current treatment information of the disabled person, and the historical care records include information on caregivers who have served the disabled person, and the caregiver information includes the name, gender, care score, personality test score, and skill assessment score of the caregiver; A prediction unit, used for inputting the basic disability information into a preset nursing prescription prediction model to perform prescription prediction, and obtaining a nursing prescription corresponding to the disabled person, wherein the nursing prescription includes basic cleaning care, cleaning care + medical care, cleaning care + spiritual comfort, and cleaning care + medical care + spiritual comfort; a determination unit, configured to determine a plurality of target caregivers corresponding to the disabled person from a preset caregiver database based on the nursing prescription corresponding to the disabled person; A scoring unit, for scoring the multiple target caregivers respectively based on the historical care records, and determining a caregiver matching the disabled person from the multiple target caregivers according to the scoring results, including: screening out historical caregivers whose care scores are greater than preset scores according to the historical care records corresponding to the disabled person, obtaining personality assessment results and skill assessment results in the basic care information of the historical caregivers, and if the personality assessment results and the skill assessment results both meet the preset assessment result requirements, using the personality assessment and the skill assessment as scoring dimensions corresponding to the multiple target caregivers, determining scoring weights corresponding to the scoring dimensions, and the scores of the multiple target caregivers respectively under the scoring dimensions, and performing weighted summation of the scores under the scoring dimensions based on the scoring weights to obtain second total scores corresponding to the multiple target caregivers respectively, determining a target caregiver with the highest second total score based on the second total scores corresponding to the multiple target caregivers respectively, and determining the target caregiver with the highest second total score as the caregiver matching the disabled person; The prediction unit is further configured to use a preset multi-layer perceptron as the preset nursing prescription prediction model, input the basic disability information into the preset multi-layer perceptron for prescription prediction, and obtain a probability value of the disabled person needing different nursing prescriptions; The prediction unit is also used to determine the nursing prescription corresponding to the maximum probability value according to the probability value of the disabled person needing different nursing prescriptions, and determine the nursing prescription corresponding to the maximum probability value as the nursing prescription corresponding to the disabled person.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images