Method, device and equipment for predicting reformed crowd suitable for aging and storage medium
The correlation between the user to be transformed and the user that has been transformed is calculated through the gray correlation analysis method, which solves the problem of vague screening standards during the aging-friendly transformation process, improves the prediction accuracy and screening efficiency, and ensures that the transformation needs of the elderly are met in a timely manner in a timely manner. .
Patent Information
- Application Number
- CN202411140221.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-29
AI Technical Summary
The screening standards during the existing aging-friendly transformation process are vague, making it difficult to accurately screen out the elderly people who need transformation the most.
Using the gray correlation analysis method, by obtaining the transformation request of the user to be transformed, a comparison sequence is generated, and the reference sequence is determined based on the classification index data of the transformed user, the correlation degree between each comparison sequence and the reference sequence is calculated, and the target is determined according to the preset rules. Renovate users.
The prediction accuracy of the people who need to be transformed in the age-friendly manner is improved, ensuring that the people who need transformation are screened out in a timely manner, avoiding the delay in the transformation application, and achieving dynamic prediction.
Smart Images

Figure CN119047634A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of aging-friendly population management, and specifically, relates to a method, device, equipment and storage medium for predicting aging-friendly transformation population. Background Art
[0002] As they age, the safety and convenience issues of the elderly in their living environment become increasingly prominent. The original buildings and designs did not take into account the special needs of the elderly, such as mobility problems, vision and hearing loss, etc. In order to improve the quality of life, safety and independence of the elderly, it is very necessary to carry out aging-friendly renovation to improve the quality of life of the elderly in their later years and enhance their happiness.
[0003] Currently, the target screening of the population for aging-friendly renovation is mainly carried out through the following stages: first, the basic information of the population to be renovated is collected, which is currently mainly collected and organized through official systems and other channels; then, the priority and specific needs of the aging-friendly renovation are determined based on the basic information.
[0004] The problem with the above screening process is that information collection is generally completed through official channels or offline manual censuses, and then based on the collected information, it is manually determined which elderly people should be arranged for renovation first. The screening criteria are vague, which makes it difficult to accurately screen out the elderly people who need renovation the most. Summary of the invention
[0005] In view of the above problems, the present application aims to provide a method, device, equipment and storage medium for predicting the population suitable for aging transformation, which are used to solve the problems of vague screening criteria and inaccurate screening results in the existing aging transformation process.
[0006] In a first aspect, the present application provides a method for predicting a population suitable for aging transformation, comprising:
[0007] Obtaining a transformation request of a user to be transformed, wherein the transformation request includes a plurality of classification indicator data;
[0008] Generate a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed;
[0009] Determine the correlation between each comparison sequence and a reference sequence using a grey correlation analysis method, wherein the reference sequence is determined based on the classification index data of the transformed user;
[0010] The target transformation user is determined according to the preset rules based on the correlation between each comparison sequence and the reference sequence.
[0011] In a possible embodiment, the determining the correlation between each comparison sequence and the reference sequence by using the grey correlation analysis method specifically includes:
[0012] Differences are taken between the corresponding elements in each comparison sequence and the reference sequence to form a difference matrix;
[0013] Determine the correlation coefficient matrix according to the difference matrix;
[0014] The degree of association between each compared sequence and the reference sequence is obtained based on the association coefficient matrix.
[0015] In a possible embodiment, determining the correlation coefficient matrix according to the difference matrix includes:
[0016] Get the maximum value Δ in the difference matrix max and the minimum value Δ min ;
[0017] Calculate the correlation coefficient ε corresponding to the element in the kth column and jth row of the difference matrix according to the following formula j (k);
[0018]
[0019] Among them, α is the resolution coefficient, Δ j (k) is the element value in the kth column and jth row of the difference matrix;
[0020] The correlation coefficients corresponding to each element in the difference matrix are combined into a correlation coefficient matrix.
[0021] In a possible embodiment, obtaining the degree of association between each comparison sequence and the reference sequence according to the association coefficient matrix specifically includes:
[0022] Determine the weight coefficient corresponding to each correlation coefficient in the correlation coefficient matrix;
[0023] The degree of association between each comparison sequence and the reference sequence is determined based on the weight coefficients and the association coefficient matrix.
[0024] In a possible embodiment, after obtaining the transformation request of the user to be transformed, the method further includes:
[0025] Filter the pending transformation requests whose classification indicators do not meet the preset requirements;
[0026] The filtered requests to be transformed are cached in batches.
[0027] In a possible embodiment, generating a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed specifically includes:
[0028] Dimensionless processing of multiple classification indicators of transformation requests;
[0029] The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed.
[0030] In a possible embodiment, before performing dimensionless processing on the multiple classification indicators of the transformation request, the method further includes:
[0031] Determine whether the user to be transformed has never been transformed or has been transformed according to the transformation request of the user to be transformed;
[0032] If the user to be transformed has never been transformed, the reference sequence is determined by averaging the classification index data of all transformed users; if the user to be transformed has been transformed before, the reference sequence is determined by the historical classification index data of the user to be transformed;
[0033] The step of generating a comparison sequence corresponding to the user to be transformed from the dimensionless processed classification index data specifically includes:
[0034] The classification index data of the to-be-transformed users who have never been transformed are used to generate a corresponding first comparison sequence, and the classification index data of the to-be-transformed users who have been transformed are used to generate a corresponding second comparison sequence.
[0035] In a second aspect, the present application also provides a device for predicting the population of people who are suitable for aging, including:
[0036] An acquisition module, which is used to acquire a transformation request of a user to be transformed, wherein the transformation request includes a plurality of classification indicator data;
[0037] A comparison sequence generation module, which generates a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed;
[0038] A correlation calculation module, which uses a grey correlation analysis method to determine the correlation between each comparison sequence and a reference sequence, wherein the reference sequence is determined based on the classification index data of the transformed user;
[0039] The target transformation user determination module is used to determine the target transformation user according to a preset rule based on the correlation between each comparison sequence and the reference sequence.
[0040] In a third aspect, the present application further provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
[0041] The memory stores computer-executable instructions;
[0042] The processor executes the computer-executable instructions stored in the memory to implement the method described in any one of the first aspects above.
[0043] In a fourth aspect, the present application further provides a computer storage medium, wherein the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method described in any one of the first aspects above.
[0044] The present application provides a method, device, equipment and storage medium for predicting the population for aging-friendly transformation. First, the transformation request of the user to be transformed is obtained, and the transformation request includes multiple classification index data; then, a comparison sequence corresponding to the user to be transformed is generated according to the transformation request of the user to be transformed; then, the correlation between each comparison sequence and the reference sequence is determined according to the classification index data of the transformed user; finally, the correlation between each comparison sequence and the reference sequence is determined according to the preset rules to determine the target transformation user. The present application uses the gray correlation analysis method to calculate the correlation between the comparison sequence determined from the user to be transformed and the reference sequence determined from the transformed user, and then sorts the users to be transformed according to the size of the correlation, so as to more accurately determine the population that needs transformation the most. Moreover, since the data of the users to be transformed are collected in a timely manner, the situation where the transformation application of the users to be transformed is delayed is avoided, and dynamic prediction of the users to be transformed is realized. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0046] Figure 1 A schematic diagram of a scenario of a method for predicting a population adapted for aging provided in an embodiment of the present application;
[0047] Figure 2 A flowchart of a method for predicting a population suitable for aging transformation provided in an embodiment of the present application;
[0048] Figure 3 A flowchart of another method for predicting the population adapted for aging provided in an embodiment of the present application;
[0049] Figure 4 A schematic diagram of the structure of a device for predicting the population adapted for aging provided in an embodiment of the present application;
[0050] Figure 5 A hardware structure diagram of an electronic device provided in an embodiment of the present application.
[0051] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments.
[0052] Description of reference numerals:
[0053] 101-first client; 102-second client; 103-server; 401-acquisition module; 402-comparison sequence generation module; 403-association calculation module; 404-target transformation user determination module; 501-processor; 502-memory; 503-communication interface; 504-communication bus. DETAILED DESCRIPTION
[0054] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0055] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.
[0056] In the embodiments of the present application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way. In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more.
[0057] It should be noted that the "at..." in the embodiment of the present application can be the instant when a certain situation occurs, or it can be a period of time after a certain situation occurs, and the embodiment of the present application does not specifically limit this. In addition, the method for predicting the population of people suitable for aging transformation provided in the embodiment of the present application is only used as an example, and the method for predicting the population of people suitable for aging transformation can also include more or less content.
[0058] As they age, the safety and convenience issues of the elderly in their living environment become increasingly prominent. The original buildings and designs did not take into account the special needs of the elderly, such as mobility problems, vision and hearing loss, etc. In order to improve the quality of life, safety and independence of the elderly, it is very necessary to carry out aging-friendly renovation to improve the quality of life of the elderly in their later years and enhance their happiness.
[0059] Currently, the target screening of the population for aging-friendly renovation is mainly carried out through the following stages: first, the basic information of the population to be renovated is collected, which is currently mainly collected and organized through official systems and other channels; then, the priority and specific needs of the aging-friendly renovation are determined based on the basic information.
[0060] The applicant found that the problem with the above screening process is that information collection is generally completed through official channels or offline manual censuses, and then based on the collected information, it is manually determined which elderly people should be arranged for renovation first. The screening criteria are vague, which makes it difficult to accurately screen out the elderly people who are most in need of renovation.
[0061] Based on the above problems, the present application provides a method, device, equipment and storage medium for predicting the population suitable for aging transformation, so as to improve the prediction accuracy of the population suitable for aging transformation.
[0062] Figure 1 A schematic diagram of a scenario of a method for predicting a population adapted for aging provided in an embodiment of the present application. Figure 1 As shown, in this application scenario, a first client 101 is included for collecting basic information of the user to be transformed. The user of the first client 101 is the user to be transformed. The first client 101 generates a transformation request from the collected basic information and sends it to the server 103. The server 103 receives the transformation request. At the same time, the server 103 stores the historical data of the transformed users. The server 103 can predict the target transformation users who meet the requirements among the users to be transformed based on the transformation request and historical data. The second client 102 can obtain the prediction results in the server at any time. The user of the second client 102 is a staff member, who can provide transformation services for the elderly according to the prediction results, thereby improving the safety and convenience of the elderly's living environment.
[0063] The first client and the second client may be electronic terminals such as mobile phones, tablets, and computers.
[0064] Figure 2 A flowchart of a method for predicting a population suitable for aging transformation provided in an embodiment of the present application, the method is applied to Figure 1 Server 103 is shown. In this embodiment, the method for predicting the population suitable for aging transformation specifically includes:
[0065] S201: Obtaining a transformation request of a user to be transformed, where the transformation request includes a plurality of classification indicator data;
[0066] The transformation request of the user to be transformed can be initiated by the user to be transformed through a terminal (such as a mobile phone), wherein the transformation request includes a plurality of classification indicator data corresponding to the user to be transformed.
[0067] In addition to filling in and collecting these classification indicator data through some official websites and other channels, you can also fill in the application through mini-programs, public accounts, etc., and you can also apply through online file sharing. If it is inconvenient for you to fill in the form yourself, you can also provide some voice assistance, or entrust your children, relatives, community elderly care consultants, neighborhood committee staff, etc. to apply on your behalf.
[0068] Since manual collection is troublesome and regular censuses will result in the problem of being unable to collect data during the window period between two censuses, the above-mentioned information collection method is conducive to users to be transformed to submit transformation applications at any time and receive timely processing.
[0069] In addition, the classification indicator data mainly includes the basic information of the users to be transformed, such as physical data, including: age, years of medication, types of underlying diseases, etc., and equipment transformation content, including: equipment classification, years of use, number of repairs, frequency of use, etc.
[0070] S202: Generate a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed
[0071] Each user to be transformed has corresponding classification index data, and these data can form a comparison series corresponding to the user to be transformed.
[0072] If the classification index data of multiple users to be transformed are obtained at the same time, multiple comparison sequences corresponding to the multiple users to be transformed can be obtained.
[0073] S203: Determine the correlation between each comparison sequence and the reference sequence using the grey correlation analysis method. The reference sequence is determined based on the classification index data of the transformed user.
[0074] The comparison sequence obtained in step S202 is analyzed for association with the reference sequence, which can be calculated by grey correlation analysis. The basic idea of grey correlation analysis is to judge whether the connection between different sequences is close based on the similarity of the geometric shapes of the sequence curves. The basic idea is to convert the discrete behavior observations of the system factors into piecewise continuous broken lines by linear interpolation, and then construct a model to measure the degree of association based on the geometric characteristics of the broken lines. The closer the broken line geometry is, the greater the association between the corresponding sequences, and vice versa.
[0075] The reference sequence is determined based on the classification indicators of transformed users. This is because transformed users are naturally more in line with the transformation requirements in terms of screening, so the data of transformed users can be used as a reference.
[0076] Specifically, assuming that multiple separate indicator data for each transformed user have been determined, then it is only necessary to average (or weight) the classification indicator data of multiple transformed users to obtain relatively simple classification indicator reference data, and the average data corresponding to these different classification indicators can constitute a reference sequence.
[0077] S204: Determine the target transformation user according to a preset rule based on the correlation between each comparison sequence and the reference sequence.
[0078] After calculating the correlation between the comparison sequence of each user to be transformed and the reference sequence, the correlation between different users to be transformed can be compared according to the preset rules. For example, the 10 users to be transformed with the largest correlation are selected for transformation every other month. The number of screenings can be adjusted as needed according to the size of the users to be transformed and the transformation team.
[0079] Figure 3 A flowchart of another method for predicting the population adapted for aging provided in an embodiment of the present application, which method can also be applied to Figure 1 The server shown in FIG. Figure 2 Based on the embodiment, the prediction method of the population suitable for aging transformation is specifically described. Figure 3 As shown in the figure, the prediction method of the population suitable for aging transformation specifically includes:
[0080] S301: Obtaining a transformation request of a user to be transformed, the transformation request including multiple classification indicator data
[0081] S302: Filter the requests to be transformed whose classification indicators do not meet the preset requirements, and cache the filtered requests to be transformed in batches
[0082] Figure 2 The premise in the illustrated embodiment is that all transformation requests meet the requirements, but in actual situations, individual classification indicator data corresponding to some users to be transformed do not meet the transformation requirements. Therefore, after obtaining the transformation requests of the users to be transformed, the method further includes: filtering the transformation requests whose classification indicators do not meet the preset requirements; and caching the filtered transformation requests in batches.
[0083] Among them, in filtering the transformation requests whose classification indicators do not meet the preset requirements, the preset requirements may be that the age of the user to be transformed must be greater than or equal to 60 years old, and if the user to be transformed has been transformed before, the age of the equipment must be greater than or equal to 3 years, etc. This can reduce the pressure of subsequent data processing.
[0084] After data filtering, qualified transformation requests can also be cached in batches. For example, every 10 users to be transformed form a queue. In this way, in subsequent calculations, 10 transformation requests of users to be transformed can be pulled each time to generate a corresponding comparison sequence, to prevent frequent subsequent processing when the number of pulls is small each time, such as when there are only one or two transformation requests, no pull processing will be performed, thereby reducing the system processing pressure.
[0085] S303: Generate a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed
[0086] In this step, generating a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed specifically includes:
[0087] Dimensionless processing of multiple classification indicators of transformation requests;
[0088] The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed.
[0089] In the classification indicator data corresponding to each transformation request, since most of them contain dimensions, in order to eliminate the influence between data of different dimensions, it is necessary to perform dimensionless processing on multiple classification indicators of the transformation request; and generate a comparison sequence corresponding to the user to be transformed from the dimensionless processed classification indicator data.
[0090] The dimensionless processing process is as follows:
[0091] Assume that the data to be processed by batch-pulling n transformation requests is:
[0092]
[0093] Each column corresponds to a comparison sequence, record The average value of all elements in Then the comparison sequence of n transformation requests after dimensionless processing is:
[0094]
[0095] After obtaining the comparison sequence without quantization processing, the correlation between the comparison sequence and the reference sequence can be calculated by the following steps. The specific steps are as follows:
[0096] S304: Differences are taken between the corresponding elements in each comparison sequence and the reference sequence to form a difference matrix
[0097] According to step S203, the reference sequence x(0) can be obtained by averaging the classification index data of multiple transformed users. For example, the elements in x(0) are obtained by averaging the corresponding branch index data of all or part of the transformed users. Since the comparison sequence is dimensionless, the corresponding branch index data of the transformed users also need to be dimensionless before obtaining the corresponding reference sequence.
[0098] Assume that the element value of the jth row and kth column in the difference matrix is Δ j (k), then:
[0099] Δ j (k)=|x j (k)-x j (0)|
[0100] Among them, x j (k) is the element in row j and column k of X, x j (0) is the j-th row element in the reference sequence, j = 1, 2, ..., m, k = 1, 2, ..., n, and m is the number of classification indicators.
[0101] S305: Determine the correlation coefficient matrix based on the difference matrix
[0102] First determine the maximum value Δ in the difference matrix max and the minimum value Δ min ;
[0103] Calculate the correlation coefficient ε corresponding to the element in the kth column and jth row of the difference matrix according to the following formula j (k);
[0104]
[0105] Among them, α is the resolution coefficient, which is generally set to 0.5 to prevent the influence of extreme values on the correlation degree, and ε j (k) is the element value of the jth row and kth column in the correlation coefficient matrix.
[0106] The correlation coefficient matrix can be obtained through the above operations.
[0107] S306: Obtain the correlation between each comparison sequence and the reference sequence according to the correlation coefficient matrix
[0108] In this step, the correlation between each comparison sequence and the reference sequence is obtained according to the correlation coefficient matrix, which specifically includes:
[0109] Determine the weight coefficient corresponding to each correlation coefficient in the correlation coefficient matrix;
[0110] The degree of association between each comparison sequence and the reference sequence is determined based on the weight coefficients and the association coefficient matrix.
[0111] The correlation between the comparison sequence and the reference sequence can be determined by the correlation coefficient matrix. For example, the correlation between the first comparison sequence and the reference sequence can be determined by the correlation coefficient of the corresponding column of the correlation coefficient matrix. Assuming that the correlation of the kth comparison sequence is T(k), then:
[0112]
[0113] In the above embodiment, the calculation of the association degree does not take into account the weight coefficient of each classification indicator, which may lead to biased evaluation results or fail to reflect the actual situation. Since each classification indicator has its own importance in the overall evaluation system, this embodiment introduces a corresponding weight coefficient for each classification indicator, so as to better evaluate the association degree between the comparison sequence and the reference sequence.
[0114] In the prior art, the weight coefficient can generally be determined by empirical value, expert score or analytic hierarchy process (AHP). This embodiment uses the following method to calculate the weight coefficient:
[0115]
[0116] In this way, the correlation degree T(k) can be optimized as:
[0117]
[0118] S307: Determine the target transformation user according to the preset rules based on the correlation between each comparison sequence and the reference sequence
[0119] After determining the correlation between each comparison sequence and the reference sequence, they can be stored in a priority queue according to the correlation, and then the data in the priority queue can be traversed and sorted at a specified time point (considering the time period when data collection and processing are stopped, such as 21:00 to 6:00 the next day).
[0120] In order to meet the needs of people of different identities to view data, the data can be displayed to relevant personnel in different forms to facilitate the staff to review the prediction results.
[0121] After manual confirmation and transformation is completed, the updated data after transformation needs to be added to the completed data, and then the reference sequence is updated regularly every day. In the subsequent prediction process, the correlation degree of the comparison sequence is calculated with the latest reference sequence, so as to realize the prediction of the dynamics of the target transformation user.
[0122] In another embodiment, before performing dimensionless processing on multiple classification indicators of the transformation request in step S303, the method for predicting the population for transformation suitable for the elderly further includes:
[0123] Determine whether the user to be transformed has never been transformed or has been transformed according to the transformation request of the user to be transformed;
[0124] If the user to be transformed has never been transformed, the reference sequence is determined by averaging the classification index data of all transformed users; if the user to be transformed has been transformed before, the reference sequence is determined by the historical classification index data of the user to be transformed;
[0125] The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed, specifically including:
[0126] The classification index data of the to-be-transformed users who have never been transformed are used to generate a corresponding first comparison sequence, and the classification index data of the to-be-transformed users who have been transformed are used to generate a corresponding second comparison sequence.
[0127] It can be understood from the above embodiments that no matter the user to be transformed has never been transformed or has been transformed before, the classification indicator data of all transformed users can be used to determine the reference sequence.
[0128] For users who have never been transformed and are waiting to be transformed, the classification indicator data of transformed users can be used to determine the reference sequence.
[0129] In another embodiment, for users who have been transformed, in order to better predict the target transformed users, the reference sequence can be determined based on the historical classification indicator data of the users who have been transformed. It should be noted that the data of previous transformations need to be updated in time according to the current time, such as age, total medication, total number of smoking days, duration of suffering from underlying diseases, amount of exercise, etc. in the physical data, as well as equipment usage time, road surface transformation time, line aging time, etc. in the equipment transformation content.
[0130] At the same time, in the process of generating comparison sequences, since the reference sequences used in the prediction process by the users to be transformed who have never been transformed are the same, such comparison sequences can be placed separately in the first comparison sequence. When calculating the correlation, several comparison sequences can be pulled out from the first comparison sequence for calculation each time. However, the reference sequences used in the prediction process by the users to be transformed who have been transformed are different. Therefore, such comparison sequences can be placed separately in the second comparison sequence. When calculating the correlation, only one comparison sequence can be pulled out from the second comparison sequence for calculation each time.
[0131] It should be noted that for users who have been transformed and are waiting to be transformed, if multiple transformation records are stored, their reference sequence can be determined by averaging the historical classification indicator data of the transformations. The historical classification indicator data here still needs to be updated in time according to the current time.
[0132] After calculating the correlation coefficient of each classification indicator of the modification request, the correlation degree of each type of demand (such as physical data, equipment modification content, etc.) can be calculated in the manner of step S306. For example, the correlation coefficient of each classification indicator such as age, medication year, and basic disease type in the physical data is obtained in the correlation coefficient matrix, and then the correlation degree of the physical data of the user to be modified is calculated according to the weight coefficient of each classification indicator. Assume that the weight coefficient of each type of demand is Φ t (set in advance by the system), t is the demand classification number, for example, physical data is 1, equipment modification content is 2, then the urgency of each type of demand can be defined, and the calculation formula is as follows:
[0133]
[0134] Taking the demand for physical data as an example, ε j (k) is the correlation coefficient of each classification indicator (such as age, year of medication, type of underlying disease, etc.) under the physical data of the kth user to be transformed (corresponding to the kth column in the correlation coefficient matrix), ω j (k) is the weight coefficient of each classification indicator (such as age, medication year, basic disease type, etc.) under the user's physical data to be transformed, Φ 1 It represents the weight coefficient of body data. Therefore, the urgency of body data for users who have had transformation needs is Γ 1 .
[0135] Therefore, for the transformation requests made by multiple users who have been transformed, the urgency of each type of demand of each user can be obtained, and the urgency of different demands of these users can be sorted and output to the corresponding terminal of the staff. After the staff confirms, the corresponding service can be provided to the users who meet the requirements.
[0136] From the above, it can be seen that for users to be transformed who have never been transformed, the present application can sort them by calculating the correlation of the comparison sequence. For users to be transformed who have been transformed, the present application can sort them based on the correlation by calculating the urgency of each type of demand of each user to be transformed, thereby screening out target transformation users who meet the preset rules.
[0137] Figure 4 This is a schematic diagram of the structure of a device for predicting the population of aging-adapted people provided in an embodiment of the present application. The device can be in the form of software and / or hardware, such as Figure 4 As shown, the device for predicting the population suitable for aging transformation includes: an acquisition module 401, a comparison sequence generation module 402, a correlation calculation module 403 and a target transformation user determination module 404.
[0138] An acquisition module 401 is used to acquire a transformation request of a user to be transformed, where the transformation request includes a plurality of classification indicator data;
[0139] A comparison sequence generation module 402, which generates a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed;
[0140] A correlation calculation module 403, which uses a grey correlation analysis method to determine the correlation between each comparison sequence and a reference sequence, where the reference sequence is determined based on the classification index data of the transformed user;
[0141] The target transformation user determination module 404 is used to determine the target transformation user according to a preset rule based on the correlation between each comparison sequence and the reference sequence.
[0142] In a possible embodiment, the correlation calculation module 403 determines the correlation between each comparison sequence and the reference sequence using a grey correlation analysis method, specifically including:
[0143] Differences are taken between the corresponding elements in each comparison sequence and the reference sequence to form a difference matrix;
[0144] Determine the correlation coefficient matrix according to the difference matrix;
[0145] The degree of association between each compared sequence and the reference sequence is obtained based on the association coefficient matrix.
[0146] In a possible embodiment, determining the correlation coefficient matrix according to the difference matrix includes:
[0147] Get the maximum value Δ in the difference matrix max and the minimum value Δ min ;
[0148] Calculate the correlation coefficient ε corresponding to the element in the kth column and jth row of the difference matrix according to the following formula j (k);
[0149]
[0150] Among them, α is the resolution coefficient, Δ j (k) is the element value in the kth column and jth row of the difference matrix;
[0151] The correlation coefficients corresponding to each element in the difference matrix are combined into a correlation coefficient matrix.
[0152] In a possible embodiment, obtaining the degree of association between each comparison sequence and the reference sequence according to the association coefficient matrix specifically includes:
[0153] Determine the weight coefficient corresponding to each correlation coefficient in the correlation coefficient matrix;
[0154] The degree of association between each comparison sequence and the reference sequence is determined based on the weight coefficients and the association coefficient matrix.
[0155] In a possible embodiment, after obtaining the transformation request of the user to be transformed, the obtaining module 401 further includes:
[0156] Filter the pending transformation requests whose classification indicators do not meet the preset requirements;
[0157] The filtered requests to be transformed are cached in batches.
[0158] In a possible embodiment, the comparison sequence generation module 402 generates a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed, specifically including:
[0159] Dimensionless processing of multiple classification indicators of transformation requests;
[0160] The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed.
[0161] In the aforementioned embodiment, before dimensionless processing is performed on the multiple classification indicators of the transformation request, the comparison sequence generation module 402 further includes:
[0162] Determine whether the user to be transformed has never been transformed or has been transformed according to the transformation request of the user to be transformed;
[0163] If the user to be transformed has never been transformed, the reference sequence is determined by averaging the classification index data of all transformed users; if the user to be transformed has been transformed before, the reference sequence is determined by the historical classification index data of the user to be transformed.
[0164] The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed, specifically including:
[0165] The classification index data of the to-be-transformed users who have never been transformed are used to generate a corresponding first comparison sequence, and the classification index data of the to-be-transformed users who have been transformed are used to generate a corresponding second comparison sequence.
[0166] The implementation principle and technical effects of the device for predicting the population suitable for aging provided in the embodiment of the present application are the same as those of the aforementioned embodiment of the method for predicting the population suitable for aging. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned embodiment of the method for predicting the population suitable for aging.
[0167] Figure 5 A hardware structure diagram of an electronic device provided in an embodiment of the present application, such as Figure 5As shown, this embodiment provides an electronic device, including: a processor 501, and a memory 502 communicatively connected to the processor 501; the memory 502 stores computer execution instructions; the processor 501 executes the computer execution instructions stored in the memory 502, so as to implement the description of the method for predicting the population for aging-friendly transformation in the corresponding embodiment above.
[0168] Figure 5 The electronic device shown further includes a communication interface 503 and a communication bus 504 , wherein the processor 501 , the memory 502 and the communication interface 503 communicate with each other via the communication bus 504 .
[0169] The memory 502 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication bus 504 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of communication bus.
[0170] The communication interface 503 is used to connect to at least one user terminal and other network units through a network interface, and send the encapsulated IPv4 message or IPv4 message to the user terminal through the network interface.
[0171] The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 501. The above processor 501 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present disclosure can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present disclosure can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module may be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 52, and the processor 51 reads the information in the memory 52 and completes the steps of the method of the above embodiment in combination with its hardware.
[0172] The embodiment of the present application also provides a computer storage medium, in which a computer-readable storage medium stores computer-executable instructions, which are used to implement the description of the method for predicting the population suitable for aging transformation in the corresponding embodiment above when executed by the processor, so it will not be repeated here. In addition, the description of the beneficial effects of using the same method will not be repeated. For technical details not disclosed in the computer storage medium embodiment involved in the present invention, please refer to the description of the method embodiment of the present invention.
[0173] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The above-mentioned storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0174] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.
Claims
1. A method for predicting the population suitable for aging transformation, characterized in that: include: Obtaining a transformation request of a user to be transformed, wherein the transformation request includes a plurality of classification indicator data; Generate a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed; Determine the correlation between each comparison sequence and a reference sequence using a grey correlation analysis method, wherein the reference sequence is determined based on the classification index data of the transformed user; The target transformation user is determined according to the preset rules based on the correlation between each comparison sequence and the reference sequence.
2. The method according to claim 1, characterized in that: The method of using grey correlation analysis to determine the correlation between each comparison sequence and the reference sequence specifically includes: Differences are taken between the corresponding elements in each comparison sequence and the reference sequence to form a difference matrix; Determine the correlation coefficient matrix according to the difference matrix; The degree of association between each compared sequence and the reference sequence is obtained based on the association coefficient matrix.
3. The method according to claim 2, characterized in that Determining the correlation coefficient matrix according to the difference matrix includes: Get the maximum value Δ in the difference matrix max and the minimum value Δ min ; Calculate the correlation coefficient ε corresponding to the element in the kth column and jth row of the difference matrix according to the following formula j (k); Among them, α is the resolution coefficient, Δ j (k) is the element value in the kth column and jth row of the difference matrix; The correlation coefficients corresponding to each element in the difference matrix are combined into a correlation coefficient matrix.
4. The method according to claim 2, characterized in that: The step of obtaining the degree of association between each comparison sequence and the reference sequence according to the association coefficient matrix specifically includes: Determine the weight coefficient corresponding to each correlation coefficient in the correlation coefficient matrix; The degree of association between each comparison sequence and the reference sequence is determined based on the weight coefficients and the association coefficient matrix.
5. The method according to claim 1, characterized in that After obtaining the transformation request of the user to be transformed, the method further includes: Filter the transformation requests whose classification indicators do not meet the preset requirements; The filtered requests to be transformed are cached in batches.
6. The method according to claim 1, characterized in that The step of generating a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed specifically includes: Dimensionless processing of multiple classification indicators of transformation requests; The dimensionless processed classification index data is used to generate a comparison sequence corresponding to the user to be transformed.
7. The method according to claim 6, characterized in that Before performing dimensionless processing on the multiple classification indicators of the transformation request, the method further includes: Determine whether the user to be transformed has never been transformed or has been transformed according to the transformation request of the user to be transformed; If the user to be transformed has never been transformed, the reference sequence is determined by averaging the classification index data of all transformed users; if the user to be transformed has been transformed before, the reference sequence is determined by the historical classification index data of the user to be transformed; The step of generating a comparison sequence corresponding to the user to be transformed from the dimensionless processed classification index data specifically includes: The classification index data of the to-be-transformed users who have never been transformed are used to generate a corresponding first comparison sequence, and the classification index data of the to-be-transformed users who have been transformed are used to generate a corresponding second comparison sequence.
8. A device for predicting the population of people suitable for aging transformation, comprising: An acquisition module, which is used to acquire a transformation request of a user to be transformed, wherein the transformation request includes a plurality of classification indicator data; A comparison sequence generation module, which generates a comparison sequence corresponding to the user to be transformed according to the transformation request of the user to be transformed; A correlation calculation module, which uses a grey correlation analysis method to determine the correlation between each comparison sequence and a reference sequence, wherein the reference sequence is determined based on the classification index data of the transformed user; The target transformation user determination module is used to determine the target transformation user according to a preset rule based on the correlation between each comparison sequence and the reference sequence.
9. An electronic device, comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.
