Distance calculation-based method for automatically matching'old-town service 'tasks and medium

Abstract

The invention relates to a distance calculation-based old-town serving old-town task automatic matching method and a medium, and relates to the technical field of digital information processing. Performing pairwise similarity calculation on the basis of the acquired identity card address and residence address information of the inpatient and the identity card address and residence address of each medical worker in a hospital medical worker database to obtain a medical worker list with the highest similarity corresponding to a preset number threshold before each calculation; and calculating the distance between each medical worker in the medical worker list and the inpatient, calculating an integral based on the distance and a weight coefficient corresponding to the medical worker, and obtaining the old and rural medical worker list which has the highest matching degree and corresponds to a preset number threshold value, so as to realize the matching of the medical workers of the task of serving the old and rural areas by the old and rural areas. Compared with the prior art, the method can be used for quickly and accurately matching medical staff suitable for hospitalized patients.

Description

Technical Field

[0001] The present invention relates to the technical field of digital information processing, and particularly relates to an automatic matching method and medium for the "hometown fellow serving hometown fellow" task based on distance calculation. Background Art

[0002] With the development of the times and the aging process, in line with the principle of "minor illnesses can be treated in the county, and major illnesses can be treated in the city", in addition to accelerating the improvement of medical diagnosis and treatment capabilities, each district and county-level hospital also needs to improve the ability to serve patients, including improving the convenience of medical treatment, the sense of identity in medical treatment, and the satisfaction of medical treatment. However, traditional means of serving patients, such as increasing service personnel traditionally, will increase more costs, and the cost investment of using the artificial medical guidance method is also relatively high. Therefore, there is an urgent need for a medical service method with low cost and improved sense of identity and satisfaction of patients in medical treatment.

[0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The technical problem to be solved by this application is to provide an automatic matching method and medium for the "hometown fellow serving hometown fellow" task based on distance calculation, which has the characteristics of being able to quickly and accurately match the appropriate "hometown fellow" medical staff for inpatients.

[0005] In a first aspect, in one embodiment, an automatic matching method for the "hometown fellow serving hometown fellow" task based on distance calculation is provided, including: Obtain the first identity information of the inpatient, where the first identity information includes the name, ID number, ID address, and residential address information of the inpatient; Based on the ID address and residential address information of the inpatient, search the hospital medical staff database, call up the map, perform distance calculation, and find the list of medical staff of the fifth preset quantity threshold that is the closest to the ID address of the inpatient and / or the closest to the residential address, including: Perform pairwise similarity calculation on the ID address and residential address information of the obtained inpatient and the ID address and residential address of each medical staff in the hospital medical staff database, obtain the list of medical staff with the highest similarity of the corresponding preset quantity threshold for each calculation, and calculate the distance between each medical staff in the medical staff list and the inpatient; Calculate the integral based on the distance and the weight coefficient corresponding to the medical staff to obtain the list of hometown fellow medical staff of the fifth preset quantity threshold with the highest matching degree.

[0006] In one embodiment, pairwise similarity calculations are performed between the ID card address and residential address information of the hospitalized patient obtained and the ID card address and residential address of each medical staff member in the hospital medical staff database to obtain a list of medical staff members with the highest similarity for each calculation corresponding to a preset quantity threshold, and the distance between each medical staff member in the medical staff list and the hospitalized patient is calculated, including: Perform similarity calculations between the ID card address of the hospitalized patient and the ID card addresses in the hospital medical staff database to obtain a first list of medical staff members with the highest similarity corresponding to a first preset quantity threshold, and calculate the first distance between the ID card address of the hospitalized patient and the ID card addresses of each medical staff member in the first list of medical staff members; Perform similarity calculations between the ID card address of the hospitalized patient and the residential addresses in the hospital medical staff database to obtain a second list of medical staff members with the highest similarity corresponding to a second preset quantity threshold, and calculate the second distance between the ID card address of the hospitalized patient and the residential addresses of each medical staff member in the second list of medical staff members; Perform similarity calculations between the residential address of the hospitalized patient and the residential addresses in the hospital medical staff database to obtain a third list of medical staff members with the highest similarity corresponding to a third preset quantity threshold, and calculate the third distance between the residential address of the hospitalized patient and the residential addresses of each medical staff member in the third list of medical staff members; Perform similarity calculations between the residential address of the hospitalized patient and the ID card addresses in the hospital medical staff database to obtain a fourth list of medical staff members with the highest similarity corresponding to a fourth preset quantity threshold, and calculate the fourth distance between the residential address of the hospitalized patient and the ID card addresses of each medical staff member in the fourth list of medical staff members.

[0007] In one embodiment, the integral is calculated based on the distance and the weight coefficient corresponding to the medical staff member to obtain a list of fellow-townsman medical staff members with the highest matching degree corresponding to a preset quantity threshold, including: Calculate the integral of each medical staff member in the first list of medical staff members, the second list of medical staff members, the third list of medical staff members, and the fourth list of medical staff members based on each distance and the weight coefficient corresponding to the medical staff member; Obtain a list of fellow-townsman medical staff members with the highest matching degree corresponding to a fifth preset quantity threshold based on the integral of each medical staff member obtained.

[0008] In one embodiment, similarity calculation is performed based on two addresses, including: Based on the two addresses for which similarity calculation is required, both addresses are vectorized to obtain first address vector data and second address vector data; Calculate the similarity between the first address vector data and the second address vector data to obtain the similarity between the two addresses.

[0009] In one embodiment, the address is vectorized to obtain address vector data, including: Perform word segmentation on the address information, and extract the preset key address elements in the result of word segmentation; Based on the extracted key address elements, perform feature extraction, including address code extraction, address category feature extraction, and text feature extraction; Numerically process and combine the various features extracted, to form address vector data.

[0010] In one embodiment, the first distance, the second distance, the third distance, and the fourth distance are all driving distances.

[0011] In one embodiment, calculating the scores of each medical staff in the first list of medical staff, the second list of medical staff, the third list of medical staff, and the fourth list of medical staff based on the respective distances and the weight coefficients corresponding to the medical staff, includes: For any medical staff, obtain the driving distance corresponding to him / her, and based on the weight coefficient obtaining rule, obtain the weight coefficient corresponding to him / her. The weight coefficient obtaining rule includes: the weight coefficient of a doctor is lower than that of a nurse, and compared with the department where the in-patient is located, the weight coefficient of the medical staff in this in-patient department is lower than that of the medical staff in other in-patient departments; The obtaining the list of fellow-townsman medical staff with the highest matching degree and the fifth preset quantity threshold based on the scores of each medical staff obtained, includes: Based on the scores of each medical staff obtained, obtain the list of fellow-townsman medical staff with the lowest scores and the fifth preset quantity threshold, as the list of fellow-townsman medical staff with the highest matching degree and the fifth preset quantity threshold.

[0012] In one embodiment, calculating the scores of each medical staff in the first list of medical staff, the second list of medical staff, the third list of medical staff, and the fourth list of medical staff based on the respective distances and the weight coefficients corresponding to the medical staff, includes: Take the respective starting distances corresponding to each medical staff in the first list of medical staff, the second list of medical staff, the third list of medical staff, and the fourth list of medical staff as each element to form a first one-dimensional array matrix, including: A = [D1(i, j1) D2(i, j2) D3(i, j3) D4(i, j4)], Among them, A represents the first one-dimensional array matrix, i represents the index of the in-patient, j1 represents the index of the medical staff in the first medical staff list, j2 represents the index of the medical staff in the second medical staff list, j3 represents the index of the medical staff in the third medical staff list, and j4 represents the index of the medical staff in the fourth medical staff list; D1(i, j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical staff list, D2(i, j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical staff list, D3(i, j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical staff list, and D4(i, j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical staff list; Taking each weight coefficient corresponding to each medical staff in the first medical staff list, the second medical staff list, the third medical staff list, and the fourth medical staff list as each element to form a second one-dimensional array matrix, including: B = [W1(i, j1) W2(i, j2) W3(i, j3) W4(i, j4)], Among them, B represents the second one-dimensional array matrix, W1(i, j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical staff list, W2(i, j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical staff list, W3(i, j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical staff list, and W4(i, j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical staff list; Performing element-by-element multiplication on the first one-dimensional matrix and the second one-dimensional matrix to obtain a one-dimensional integral matrix, thereby obtaining the integral of each medical staff, including: C = A ⊙ B, Among them, C represents the one-dimensional matrix composed of the integrals of each medical staff, and ⊙ represents element-by-element multiplication.

[0013] In one embodiment, during the process of obtaining any medical staff list, if the similarity coefficients corresponding to the top corresponding preset number threshold of medical staff with the highest similarity coefficients are lower than the preset similarity coefficient threshold, then only the medical staff not lower than the preset similarity coefficient threshold are taken into the corresponding medical staff list; if the highest similarity coefficient is lower than the preset similarity coefficient threshold, then mark this medical staff list as a medical staff list without fellow villagers.

[0014] In a second aspect, in one embodiment, a computer-readable storage medium is provided, in which a program is stored, and the program can be loaded and executed by a processor to perform the automatic matching method described in any one of the above embodiments.

[0015] The beneficial effects of the present invention are as follows: Based on the obtained ID card address and residential address information of inpatients, pairwise similarity calculations are performed with the ID card address and residential address of each medical staff in the hospital medical staff database to obtain a list of medical staff with the highest similarity corresponding to the preset number threshold for each calculation. Then, the distance between each medical staff in the medical staff list and the inpatient is calculated, and integrals are calculated based on the distance and the weight coefficient corresponding to the medical staff, so as to obtain a list of fellow-townsman medical staff with the highest matching degree corresponding to the preset number threshold, in order to achieve the matching of medical staff for the "fellow-townsman serving fellow-townsman" task. Since similarity calculations are first performed for the first-round screening, reducing the occupation of computer resources, and then comprehensive distance and weight coefficient are used for the second-round screening, it is possible to match more accurate and suitable medical staff, thereby quickly and accurately matching the appropriate "fellow-townsman" medical staff for inpatients. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic flowchart of an automatic matching method for the "fellow-townsman serving fellow-townsman" task based on distance calculation according to an embodiment of the present application; Figure 2 is the present application Figure 2 a schematic flowchart of a method according to an embodiment of step S20; Figure 3 is the present application Figure 3 a schematic flowchart of a method according to an embodiment of step S202. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The present invention will be further described in detail below in conjunction with the accompanying drawings through specific embodiments. Similar elements in different embodiments are labeled with related similar element numbers. In the following embodiments, many details are described to enable a better understanding of the present application. However, those skilled in the art can easily recognize that some of these features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present application are not shown or described in the specification to avoid the core part of the present application being overwhelmed by excessive description. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and the general technical knowledge in the art.

[0018] In addition, the features, operations or characteristics described in the specification can be combined in any suitable manner to form various embodiments. At the same time, the steps or actions in the method description can also be reordered or adjusted in a manner obvious to those skilled in the art. Therefore, the various sequences in the specification and drawings are only for clearly describing a certain embodiment and do not mean a necessary sequence, unless it is stated that a certain sequence must be followed.

[0019] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the objects described and do not have any sequential or technical meaning.

[0020] For the convenience of explaining the inventive concept of the present application, the following briefly describes the medical service technology.

[0021] In the current medical service technology, to increase convenience, the convenience of medical services is usually increased based on the medical guidance service of client (such as mobile phone) software. However, with the intensification of the aging degree, this kind of convenience alone can no longer meet the service needs of patients. Patients need more manual services. However, if the number of service personnel is increased or manual medical guidance is adopted, the investment cost is relatively high. The applicant found in the research that if the medical staff providing medical services for inpatients is from the same hometown as the inpatients, due to the natural closeness of fellow villagers, the inpatients' sense of identity and belonging to the hospital will be stronger. Therefore, "fellow villager" medical staff can be arranged for inpatients as much as possible, so that on the basis of improving patient satisfaction, the medical service cost can be reduced. However, the applicant also found in the research that in providing medical services for inpatients, the probability of matching "fellow villager" medical staff is relatively small, which is relatively difficult to implement, and how to quickly and accurately match suitable "fellow villager" medical staff has also become a major problem.

[0022] In view of this, the embodiments of the present application provide a method and medium for automatically matching the "fellow villager serving fellow villager" task based on distance calculation. In this solution, pairwise similarity calculations are performed between the ID card address and residential address information of the inpatients obtained and the ID card address and residential address of each medical staff in the hospital medical staff database to obtain a list of medical staff with the highest similarity corresponding to a preset number threshold for each calculation, and the distance between each medical staff in the medical staff list and the inpatients is calculated. Integrals are calculated based on the distance and the weight coefficient corresponding to the medical staff to obtain a list of fellow villager medical staff with the highest matching degree corresponding to the preset number threshold, so as to realize the matching of medical staff for the "fellow villager serving fellow villager" task. First, similarity calculations are performed for the first-round screening to reduce the occupation of computer resources, and then the distance and weight coefficient are comprehensively considered for the second-round screening to match more accurate and suitable medical staff, so that suitable "fellow villager" medical staff for inpatients can be quickly and accurately matched.

[0023] An automatic matching method for the "fellow villagers serving fellow villagers" task based on distance calculation provided in the embodiments of the present application, please refer to Figure 1 , including: Step S10, obtaining the first identity information of inpatients.

[0024] Among them, the first identity information includes the name, ID number, ID address and residential address information of the inpatients. If the ID address and the residential address information are the same, the same address information is filled in both address information.

[0025] Step S20, based on the ID address and residential address information of the inpatients, search the hospital medical staff database, call the map, perform distance calculation, and find the list of the fifth preset number threshold of medical staff who are the closest to the ID address of the inpatients and / or the closest to the residential address.

[0026] The hospital medical staff database stores the second identity information of each medical staff in the hospital. The second identity information may include the name, gender, age, contact number, professional classification, rank, department where they are located, ID number, ID address and residential address of the medical staff.

[0027] In one embodiment, please refer to 2, step S20 may include: Step S201, perform pairwise similarity calculation on the ID address and residential address information of the obtained inpatients and the ID address and residential address of each medical staff in the hospital medical staff database, obtain the list of medical staff with the highest similarity of the corresponding preset number threshold for each calculation, and calculate the distance between each medical staff in the medical staff list and the inpatients.

[0028] In one embodiment, step S201 includes: Step S2011, perform similarity calculation on the ID address of the inpatients and the ID address in the hospital medical staff database, obtain the list of the first medical staff of the first preset number threshold with the highest similarity, and calculate the first distance between the ID address of the inpatients and the ID address of each medical staff in the list of the first medical staff.

[0029] In one embodiment, the similarity calculation based on two addresses includes: Step S100, based on the two addresses for which similarity calculation is required, vectorize both addresses to obtain the first address vector data and the second address vector data.

[0030] Specifically, if the similarity between the ID card address of an in-patient and the ID card address in the hospital medical staff database is calculated, the ID card address of the in-patient is vectorized to obtain the first address vector data, and the ID card address of the medical staff is vectorized to obtain the second address vector data.

[0031] To vectorize an address to obtain address vector data, some methods of the existing technology can be used. In one embodiment, the present application provides a new method, which may include: Step S1001: Perform word segmentation on the address information and extract the preset key address elements from the result of the word segmentation.

[0032] Among them, word segmentation processing includes using a word segmentation tool in natural language processing technology to split the address information into individual words or phrases. For example, splitting "XX Road, XX District, XX City, XX No." into "XX City", "XX District", "XX Road", "XX No.", etc.

[0033] Address element processing includes extracting key address elements from the result after word segmentation, such as province, city, county (district), street, house number, etc. Resources such as a place name database and an address dictionary can be used, combined with rule matching and machine learning algorithms, to identify and extract these elements.

[0034] Step S1002: Based on the extracted key address elements, perform feature extraction, including address code extraction, address category feature extraction, and text feature extraction.

[0035] Among them, address code extraction includes converting the address into geographical coordinates (such as longitude and latitude), which can be implemented by calling a geocoding service interface in one embodiment. For example, using the geocoding API provided by Baidu Maps, Gaode Maps, etc., inputting the address information, and obtaining the corresponding longitude and latitude coordinates as an important feature vector.

[0036] Address category feature extraction includes extracting some address category features according to the characteristics of the address, such as the city level to which the address belongs, whether it is a rural address, whether it is a commercial address, etc. These category features can be determined by establishing an address classification model or using predefined rules and converted into numerical features.

[0037] Text feature extraction includes extracting features from the text information in the address, such as methods like the bag-of-words model and TF-IDF. The bag-of-words model takes the words in the address as features and counts the frequency of each word; TF-IDF can measure the importance of a word in the address text and highlight the representative word features.

[0038] Step S1003: Numerically process and combine the various features extracted to form address vector data.

[0039] Numerically process the various features extracted by the feature extraction so that the computer can understand and process them. For categorical features, one-hot encoding, label encoding, etc. can be used to convert them into numerical vectors. For example, for the categorical feature of "city level", if there are categories such as "first-tier cities", "second-tier cities", "third-tier cities", etc., one-hot encoding can be used to represent them as vectors such as [1, 0, 0], [0, 1, 0], [0, 0, 1].

[0040] Combine the numerically processed various feature vectors to form the final address vector data. For example, the longitude and latitude coordinates, address category feature vectors, text feature vectors, etc. are concatenated together in a certain order to form a complete vector for subsequent data analysis, machine learning and other tasks.

[0041] Based on the above method for obtaining address vector data, since in feature extraction, the extracted features include address encoding, address category features and text features, the similarity between two addresses can be expressed more precisely, and thus a more accurate match can be obtained.

[0042] Step S200, calculate the similarity between the first address vector data and the second address vector data to obtain the similarity between the two addresses.

[0043] Those skilled in the art can understand that the similarity algorithm here can adopt the vector similarity algorithm of the prior art, which will not be elaborated here.

[0044] In one embodiment, the first distance is the driving distance. Those skilled in the art can understand that after obtaining the two address information, a map (such as Baidu Map, Tencent Map, Amap, etc.) can be called to calculate the driving distance between the two address information.

[0045] Through distance calculation, a one-dimensional distance array matrix D1(i, j1) composed of the distances corresponding to each medical staff in the first list of medical staff can be obtained, where i represents the index of the in-patient and j1 represents the index of the medical staff in the first list of medical staff.

[0046] In one embodiment, the first preset quantity threshold = 3. If the distances corresponding to each medical staff in the first list of medical staff are 15 kilometers, 25 kilometers, and 30 kilometers respectively, then D1(i, 1) = 15 kilometers, D1(i, 2) = 25 kilometers, D1(i, 3) = 30 kilometers, and then D1(i, j1) = [15 25 30].

[0047] In one embodiment, during the process of obtaining any list of medical staff, if there is a situation where the similarity coefficients corresponding to the top corresponding preset quantity threshold of medical staff with the highest similarity coefficients are lower than the preset similarity coefficient threshold, only the medical staff not lower than the preset similarity coefficient threshold are taken into the corresponding list of medical staff; if the highest similarity coefficient is lower than the preset similarity coefficient threshold, mark this list of medical staff as having no fellow-townsman medical staff.

[0048] Taking the process of obtaining the first list of medical staff as an example, if the first preset quantity threshold is 3 and the corresponding similarity coefficient threshold is 50%, then if there is a situation where the similarity coefficients corresponding to the top three medical staff with the highest similarity coefficients are lower than 50%, take the medical staff with similarity coefficients not lower than 50% into the first list of medical staff. For example, if the first two are higher than 50% and the third is lower than 50%, then the first list of medical staff only includes those two medical staff with similarity coefficients higher than 50%. If the similarity coefficient of the medical staff with the highest similarity coefficient is also lower than 50%, mark the first list of medical staff as having no fellow-townsman medical staff.

[0049] Step S2012: Calculate the similarity between the ID card address of the in-patient and the residential address in the hospital medical staff database to obtain the second list of medical staff with the highest similarity corresponding to the second preset quantity threshold, and calculate the second distance between the ID card address of the in-patient and the residential address of each medical staff in the second list of medical staff.

[0050] In one embodiment, for the similarity calculation of two addresses, the process from step S100 to step S200 can be referred to.

[0051] In one embodiment, the second distance is the driving distance.

[0052] Through distance calculation, a one-dimensional distance array matrix D2(i, j2) composed of the distances corresponding to each medical staff in the second list of medical staff can be obtained, where j2 represents the index of the medical staff in the second list of medical staff.

[0053] In one embodiment, the second preset quantity threshold = 3. If the distances corresponding to each medical staff in the second list of medical staff are 13 kilometers, 20 kilometers, and 40 kilometers respectively, then D2(i, 1) = 13 kilometers, D2(i, 2) = 20 kilometers, D2(i, 3) = 40 kilometers, and then D2(i, j2) = [13 20 40].

[0054] Step S2013: Calculate the similarity between the residential address of the in-patient and the residential addresses in the hospital medical staff database to obtain a third list of medical staff with the highest similarity and meeting the third preset quantity threshold, and calculate the third distance between the residential address of the in-patient and the residential address of each medical staff in the third list of medical staff.

[0055] In one embodiment, for the similarity calculation of two addresses, the process from step S100 to step S200 can be referred to.

[0056] In one embodiment, the third distance is the driving distance.

[0057] Through distance calculation, a one-dimensional distance array matrix D3(i, j3) composed of the distances corresponding to each medical staff in the third list of medical staff can be obtained, where j3 represents the index of the medical staff in the third list of medical staff.

[0058] In one embodiment, the third preset quantity threshold = 3. If the distances corresponding to each medical staff in the third list of medical staff are 27 kilometers, 30 kilometers, and 35 kilometers respectively, then D3(i, 1) = 27 kilometers, D3(i, 2) = 30 kilometers, D3(i, 3) = 35 kilometers, and D3(i, j3) = [27 30 35].

[0059] Step S2014: Calculate the similarity between the residential address of the in-patient and the ID card addresses in the hospital medical staff database to obtain a fourth list of medical staff with the highest similarity and meeting the fourth preset quantity threshold, and calculate the fourth distance between the residential address of the in-patient and the ID card address of each medical staff in the fourth list of medical staff.

[0060] In one embodiment, for the similarity calculation of two addresses, the process from step S100 to step S200 can be referred to.

[0061] In one embodiment, the fourth distance is the driving distance.

[0062] Through distance calculation, a one-dimensional distance array matrix D4(i, j4) composed of the distances corresponding to each medical staff in the fourth list of medical staff can be obtained, where j4 represents the index of the medical staff in the fourth list of medical staff.

[0063] In one embodiment, the fourth preset quantity threshold = 3. If the distances corresponding to each medical staff in the fourth list of medical staff are 10 kilometers, 17 kilometers, and 23 kilometers respectively, then D4(i, 1) = 10 kilometers, D4(i, 2) = 17 kilometers, D4(i, 3) = 23 kilometers, and D4(i, j4) = [10 17 23].

[0064] In the research, the applicant found that if the map is directly called for distance calculation, since each distance calculation occupies a large amount of computer resources, a large number of distance calculations will consume a large amount of computer resources.

[0065] In view of this, in the embodiments of the present application, first, similarity calculation is performed according to the addresses, and the "fellow villager medical staff" closer to the address of the in-patient is screened out by the address similarity algorithm, and then the actual distance is calculated based on the screening result for further screening. In this way, the occupation of computer resources can be reduced.

[0066] Step S202: Calculate the integral based on the distance and the weight coefficient corresponding to the medical staff, and obtain the list of the fifth preset number threshold of fellow villager medical staff with the highest matching degree.

[0067] In one embodiment, please refer to Figure 3 , step S202 may include: Step S2021: Calculate the integral of each medical staff in the first list of medical staff, the second list of medical staff, the third list of medical staff, and the fourth list of medical staff based on each distance and the weight coefficient corresponding to the medical staff.

[0068] In one embodiment, step S2021 may include: For any medical staff, obtain the driving distance corresponding to him, and obtain the weight coefficient corresponding to him based on the weight coefficient obtaining rule.

[0069] In one embodiment, the weight coefficient obtaining rule includes: The weight coefficient of a doctor is lower than that of a nurse, and compared with the department where the in-patient is located, the weight coefficient of the medical staff in this in-patient department is lower than that of the medical staff in other in-patient departments.

[0070] Then in a specific implementation, step S2021 may include: Step S1000: Take each starting distance corresponding to each medical staff in the first list of medical staff, the second list of medical staff, the third list of medical staff, and the fourth list of medical staff as each element to form a first one-dimensional array matrix, including: A = [D1(i, j1) D2(i, j2) D3(i, j3) D4(i, j4)], Among them, A represents the first one-dimensional array matrix, i represents the index of the in-patient, j1 represents the index of the medical staff in the first medical staff list, j2 represents the index of the medical staff in the second medical staff list, j3 represents the index of the medical staff in the third medical staff list, and j4 represents the index of the medical staff in the fourth medical staff list; D1(i, j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical staff list, D2(i, j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical staff list, D3(i, j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical staff list, and D4(i, j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical staff list.

[0071] Step S2000, taking the respective weight coefficients corresponding to each medical staff in the first medical staff list, the second medical staff list, the third medical staff list, and the fourth medical staff list as elements to form a second one-dimensional array matrix, including: B = [W1(i, j1) W2(i, j2) W3(i, j3) W4(i, j4)], where B represents the second one-dimensional array matrix, W1(i, j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical staff list, W2(i, j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical staff list, W3(i, j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical staff list, and W4(i, j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical staff list.

[0072] Step S3000, multiplying the first one-dimensional matrix and the second one-dimensional matrix element by element to obtain a one-dimensional integral matrix, thereby obtaining the integral of each medical staff, including: C = A ⊙ B, where C represents the one-dimensional matrix composed of the integrals of each medical staff, and ⊙ represents element-by-element multiplication.

[0073] Through steps S1000 to S3000, a one-dimensional array containing the integrals of each medical staff in each medical staff list can be obtained. Based on this, the integrals in this one-dimensional array can be sorted.

[0074] Step S2022, obtaining a list of fellow-townsman medical staff with the highest matching degree and a fifth preset quantity threshold based on the integrals of each medical staff obtained.

[0075] In one embodiment, step S2022 may include: obtaining a list of fellow-townsman medical staff with the lowest scores based on the scores of each medical staff, and using it as a list of fellow-townsman medical staff with the highest matching degree and a fifth preset quantity threshold. According to steps S1000 to S3000, if the scores are sorted in ascending order, a list of fellow-townsman medical staff with the highest matching degree and a fifth preset quantity threshold can be obtained. In one embodiment, the fifth preset quantity threshold = 3, and the top three medical staff with the lowest scores can be selected as the three fellow-townsman medical staff with the highest matching degree.

[0076] In one embodiment, compared with the department where the in-patient is located, the weight coefficient of a doctor in the same department as the in-patient is 1, the weight of a nurse in the same department as the in-patient is 2, the weight coefficient of a doctor in other departments is 3, and the weight coefficient of a nurse in other departments is 4. In this way, fellow-townsman medical staff in the same department as the in-patient are preferably matched for the in-patient, and doctors are preferably matched to further improve the satisfaction of the in-patient.

[0077] Based on the automatic matching method of any of the above embodiments, similarity calculation is first performed for the first-round screening to reduce the occupation of computer resources, and then distance and weight coefficient are comprehensively considered for the second-round screening to match more accurate and suitable medical staff. In this way, a suitable "fellow-townsman" medical staff for the in-patient can be quickly and accurately matched.

[0078] The automatic matching method in the embodiment of the present application further includes: based on the obtained list of fellow-townsman medical staff, determining a specific medical staff who will conduct on-site condolence services for the in-patient within the future time threshold range, and using this medical staff as the matching person for the "fellow-townsman serving fellow-townsman" task.

[0079] In one embodiment of the present application, a computer-readable storage medium is provided, and a program is stored on the storage medium. The stored program includes the method that can be loaded and processed by a processor in any of the above embodiments.

[0080] Those skilled in the art can understand that all or part of the functions of the various methods in the above embodiments can be implemented by hardware or by computer programs. When all or part of the functions in the above embodiments are implemented by computer programs, the programs can be stored in a computer-readable storage medium, which can include: read-only memory, random access memory, magnetic disks, optical disks, hard disks, etc. The above functions can be realized by a computer executing these programs. For example, store the program in the memory of the device. When the processor executes the program in the memory, the above-mentioned all or part of the functions can be realized. In addition, when all or part of the functions in the above embodiments are implemented by computer programs, the programs can also be stored in storage media such as servers, other computers, magnetic disks, optical disks, flash drives or mobile hard disks, and saved to the memory of the local device by downloading or copying, or the system of the local device can be updated. When the processor executes the program in the memory, all or part of the functions in the above embodiments can be realized.

[0081] The above uses specific examples to elaborate on the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art of the present invention, according to the idea of the present invention, several simple deductions, deformations or substitutions can also be made.

Claims

1. An automatic matching method for the task of "fellow villagers serving fellow villagers" based on distance calculation, characterized in that: include: Acquire the first identity information of the inpatient, wherein the first identity information includes the name, ID card number, ID card address and residence address information of the inpatient; Based on the ID card address and residence address information of the inpatient, searching the hospital medical staff database, calling the map, performing distance calculation, and finding a list of medical staff with a fifth preset number threshold closest to the inpatient ID card address and / or closest to the residence address, including: Based on the acquired ID card address and residence address information of the inpatient, the similarity calculation is performed with the ID card address and residence address of each medical staff in the hospital medical staff database, and the list of medical staff with the highest similarity corresponding to the preset number threshold before each calculation is obtained, and the distance between each medical staff in the list of medical staff and the inpatient is calculated; The points are calculated based on the weight coefficients corresponding to the distance and the medical staff, and a list of fellow medical staff with the fifth preset number threshold having the highest matching degree is obtained.

2. The automatic matching method according to claim 1, characterized in that: The above-mentioned similarity calculation is performed based on the obtained ID card address and residence address information of the inpatient and the ID card address and residence address of each medical staff in the hospital medical staff database to obtain a list of medical staff with the highest similarity corresponding to a preset number threshold before each calculation, and the distance between each medical staff in the medical staff list and the inpatient is calculated, including: Calculate the similarity between the ID card address of the inpatient and the ID card address in the hospital medical staff database to obtain a first list of medical staff with a first preset number threshold with the highest similarity, and calculate the first distance between the ID card address of the inpatient and the ID card address of each medical staff in the first list of medical staff; Calculate the similarity between the ID card address of the inpatient and the residence address in the hospital medical staff database to obtain a second list of medical staff with a second preset number threshold with the highest similarity, and calculate the second distance between the ID card address of the inpatient and the residence address of each medical staff in the second list of medical staff; Calculate the similarity between the residential address of the inpatient and the residential address in the hospital medical staff database to obtain a third list of medical staff with a third preset number threshold with the highest similarity, and calculate the third distance between the residential address of the inpatient and the residential address of each medical staff in the third list of medical staff; The similarity between the residential address of the inpatient and the ID card address in the hospital medical staff database is calculated to obtain a fourth list of medical staff with a fourth preset number threshold with the highest similarity, and the fourth distance between the residential address of the inpatient and the ID card address of each medical staff in the fourth medical staff list is calculated.

3. The automatic matching method according to claim 2, characterized in that: The aforementioned weight coefficient calculation based on the distance and the corresponding medical staff is used to calculate the integral, and obtain a list of fellow medical staff with the highest matching degree corresponding to the preset number threshold, including: Calculate the score of each medical staff in the first medical staff list, the second medical staff list, the third medical staff list and the fourth medical staff list based on the weight coefficient corresponding to each distance and medical staff; Based on the points obtained for each medical staff, a list of fellow medical staff with the highest matching degree and the fifth preset number threshold is obtained.

4. The automatic matching method according to claim 1, characterized in that: Similarity calculation based on two addresses, including: Based on two addresses that need to be calculated for similarity, both addresses are vectorized to obtain first address vector data and second address vector data; The similarity between the first address vector data and the second address vector data is calculated to obtain the similarity between the two addresses.

5. The automated routing method for inpatient medical service information according to claim 4, characterized in that: Vectorize the address to obtain address vector data, including: Perform word segmentation processing on the address information and extract preset key address elements from the word segmentation processing result; Based on the extracted key address elements, feature extraction is performed, including address code extraction, address category feature extraction and text feature extraction; The various features extracted are digitized and combined to form address vector data.

6. The automatic matching method according to claim 3, characterized in that: The first distance, the second distance, the third distance and the fourth distance are all driving distances.

7. The automatic matching method according to claim 6, characterized in that: The calculation of the points of each medical staff in the first medical staff list, the second medical staff list, the third medical staff list and the fourth medical staff list based on the weight coefficients corresponding to each distance and medical staff includes: For any medical staff, the driving distance corresponding to the medical staff is obtained, and based on the weight coefficient acquisition rule, the weight coefficient corresponding to the medical staff is obtained, wherein the weight coefficient of the doctor is lower than the weight coefficient of the nurse, and compared with the department where the inpatient is located, the weight coefficient of the medical staff of the inpatient department is lower than the weight coefficient of the medical staff of other inpatient departments; The list of fellow medical staff with the highest matching degree of the fifth preset number threshold obtained based on the points obtained for each medical staff includes: Based on the points obtained for each medical staff, a list of fellow medical staff with the lowest points within the fifth preset number threshold is obtained, which is used as the list of fellow medical staff with the highest matching degree within the fifth preset number threshold.

8. The automatic matching method according to claim 6, characterized in that: The calculation of the points of each medical staff in the first medical staff list, the second medical staff list, the third medical staff list and the fourth medical staff list based on the weight coefficients corresponding to each distance and medical staff includes: The starting distances corresponding to each medical staff in the first medical staff list, the second medical staff list, the third medical staff list and the fourth medical staff list are used as elements to form a first one-dimensional array matrix, including: A=[D1(i,j1) D2(i,j2) D3(i,j3) D4(i,j4)], Among them, A represents the first one-dimensional array matrix, i represents the index of the inpatient, j1 represents the index of the medical staff in the first medical staff list, j2 represents the index of the medical staff in the second medical staff list, j3 represents the index of the medical staff in the third medical staff list, and j4 represents the index of the medical staff in the fourth medical staff list; D1(i,j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical staff list, D2(i,j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical staff list, D3(i,j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical staff list, and D4(i,j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical staff list; The weight coefficients corresponding to each medical staff in the first medical staff list, the second medical staff list, the third medical staff list and the fourth medical staff list are used as elements to form a second one-dimensional array matrix, including: B=[W1(i,j1) W2(i,j2) W3(i,j3) W4(i,j4)], Wherein, B represents the second one-dimensional array matrix, W1(i,j1) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the first medical and nursing people's list, W2(i,j2) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the second medical and nursing people's list, W3(i,j3) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the third medical and nursing people's list, and W4(i,j4) represents the one-dimensional distance array matrix composed of the distances corresponding to each medical staff in the fourth medical and nursing people's list; The first one-dimensional matrix and the second one-dimensional matrix are multiplied element by element to obtain a one-dimensional integral matrix, thereby obtaining the score of each medical staff member, including: C=A⊙B, Among them, C represents the one-dimensional matrix composed of the points of each medical staff, and ⊙ represents element-by-element multiplication.

9. The automatic matching method according to claim 2, characterized in that: In the process of obtaining any list of medical staff, if the similarity coefficient corresponding to the medical staff with the highest similarity coefficient before the preset number threshold is lower than the preset similarity coefficient threshold, only the medical staff with a similarity coefficient not lower than the preset similarity coefficient threshold will be added to the corresponding list of medical staff; if the highest similarity coefficient is lower than the preset similarity coefficient threshold, the list of medical staff will be marked as having no fellow medical staff.

10. A computer-readable storage medium, characterized in that: The medium stores a program, which can be loaded by a processor and execute the automatic matching method according to any one of claims 1 to 9.

Images