Business planning method, device and equipment and storage medium thereof

Abstract

The embodiment of the invention belongs to the technical field of financial science and technology, is applied to an insurance scheme planning adjustment scene, and relates to a business planning method, device and equipment and a storage medium thereof.The method comprises the steps that position information of a target school and multi-dimensional feature data influencing task planning are obtained; predicting category information of the target school; and constructing a task planning scheme of the target school according to the task planning schemes corresponding to the other schools of the same category. Particularly in a level-of-learning insurance pricing and clause setting scene, the task planning method can be adopted to determine a school category according to regional position information and multi-dimensional social environment factors of a target school, and a level-of-learning insurance pricing and clause planning scheme is constructed according to level-of-learning insurance pricing and clause setting of all schools in the school category. The method can fully combine the regional actual living standard and regional diversity, and flexibly generates the level insurance buying scheme for students in different regions by taking a school as a unit, and is more scientific and reasonable.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and is applied to insurance plan planning and adjustment scenarios, and in particular to a business planning method, device, equipment and storage medium thereof. Background Art

[0002] School insurance is a type of insurance that provides accident and medical protection for teenagers. In order to cover as many students as possible, the sales of school insurance are generally connected to schools for unified underwriting. However, the existing school insurance coverage plan planning is generally based on existing customers, using the insured's information to predict possible risks in the future. However, for new customers without existing information, or customers from new schools / new regions, most insurance companies can only simply divide the insurance plans for students from different schools by age.

[0003] However, planning the school insurance plan only from the student level is not comprehensive enough in terms of planning considerations. Moreover, with a large number of students, there will be a lot of data to process, and the planning plan will be more complicated, which will seriously consume planning resources and is not scientific and rational enough. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a business planning method, device, equipment and storage medium thereof to solve the problem that the existing school insurance plan is only planned from the student level, resulting in the business planning being not scientific and rational enough.

[0005] In order to solve the above technical problems, the embodiment of the present application provides a service planning method, which adopts the following technical solutions:

[0006] A business planning method comprises the following steps:

[0007] Get the location information of the target school;

[0008] Acquire multidimensional feature data that has an impact on task planning for the target school;

[0009] Input the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and output the category information of the target school after prediction;

[0010] Using the category information, filter out other schools belonging to the same category as the target school from historical stock data;

[0011] Obtaining task planning solutions corresponding to the other schools respectively;

[0012] According to the task planning plans corresponding to the other schools, a task planning plan for the target school is constructed to complete the task planning for the target school.

[0013] Furthermore, before executing the step of inputting the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model and outputting the category information of the target school after prediction, the method further includes:

[0014] Acquire model training data and preprocess the model training data, wherein the model training data includes pre-collected location information of a batch of schools and the multidimensional feature data that has an impact on task planning for each school in the batch of schools;

[0015] The preprocessed model training data is input into the school category prediction model to be trained, and the school category prediction model to be trained is pre-trained to obtain a pre-trained school category prediction model.

[0016] Furthermore, the step of preprocessing the model training data specifically includes:

[0017] Obtaining distinguishing identification information of each school in the batch of schools, wherein the distinguishing identification information includes school name information or school distinguishing code information;

[0018] According to the distinguishing identification information, the location information and the multi-dimensional feature data corresponding to the same school are filtered out from the model training data as a filtering result;

[0019] Based on the screening results, group training data corresponding to each school in the batch of schools is generated to complete the preprocessing of the model training data.

[0020] Furthermore, the step of pre-training the school category prediction model to be trained specifically includes:

[0021] Obtaining the importance coefficients pre-set according to the position information and the importance coefficients respectively set for the multi-dimensional features corresponding to the multi-dimensional feature data;

[0022] Using the preset comprehensive representation distance algorithm:

[0023]

[0024] Calculate the comprehensive representation distance between two schools in the batch of schools, D s represents the comprehensive characterization distance,

[0025] In the formula, ω x ·|xi -x j |+ω y ·|y i -y j |+ω z ·|z i -z j | represents the location distance value of schools numbered i and j, x represents longitude, y represents latitude, z represents altitude, ω x ,ω y and ω z They represent the longitude importance coefficient, latitude importance coefficient and altitude importance coefficient respectively.

[0026] In the formula, represents the total distance value of the characteristics of schools numbered i and j in the k dimensions, k represents the number of dimensions of the multi-dimensional feature, |a ik -a jk | represents the characteristic distance value of schools numbered i and j in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension;

[0027] Clustering the batch of schools according to the comprehensive representation distance between any two schools in the batch of schools and the preset number of clustering clusters to obtain school categories equal to the number of clustering clusters;

[0028] Calculate the average value based on the location information of all schools included in each cluster and the multidimensional feature data to obtain the location information of the proposed center point of each cluster and the multidimensional feature data;

[0029] The location information of the proposed center point of each cluster and the multi-dimensional feature data are set as the category identification data of each school category, so as to complete the pre-training of the school category prediction model to be trained.

[0030] Furthermore, the step of clustering the batch of schools according to the comprehensive representation distance between any two schools in the batch of schools and the preset number of clustering clusters to obtain the same number of school categories as the number of clustering clusters specifically includes:

[0031] The comprehensive representation distance between any two schools in the batch of schools and the preset number of clusters are used as clustering parameters;

[0032] The batch of schools is clustered using a K-means clustering algorithm to obtain school categories equal in number to the number of clusters.

[0033] Furthermore, the step of inputting the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and outputting the category information of the target school after prediction, specifically includes:

[0034] Get category identification data for each school category;

[0035] According to the category identification data of each school category, identifying the location information of the proposed center point of each cluster and the multi-dimensional feature data;

[0036] Using the preset comprehensive representation distance algorithm:

[0037]

[0038] Calculate the comprehensive representation distance between the target school and the proposed center point of each cluster, D p represents the comprehensive characterization distance,

[0039] In the formula, x p ,y p and z p Together, they represent the location information of the target school. Specifically, x p Indicates the longitude of the target school, y p represents the latitude of the target school, z p represents the altitude of the target school, and correspondingly, x o ,y o and z o Together they represent the location information of the proposed center point of the current cluster. Specifically, x o Indicates the longitude of the target school, y o represents the latitude of the target school, z o represents the altitude of the target school, ω x ,ω y and ω z represent the longitude importance coefficient, the latitude importance coefficient and the altitude importance coefficient respectively,

[0040] In the formula, represents the total feature distance value between the target school and the proposed center point of the current cluster in the k dimensions, where k represents the number of dimensions of the multi-dimensional feature, |a pk -a ok | represents the characteristic distance value between the target school and the proposed center point of the current cluster in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension;

[0041] According to the comprehensive representation distance between the target school and the proposed center point of each cluster, the proposed center point with the smallest comprehensive representation distance to the target school is selected as the target center point;

[0042] The school category corresponding to the target center point is used as the category information of the target school, and model output processing is performed.

[0043] Furthermore, the step of constructing a task planning scheme for the target school according to the task planning schemes corresponding to the other schools to complete the task planning for the target school includes:

[0044] According to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension;

[0045] The task index values ​​corresponding to the other schools in the target resolution dimension are averaged to obtain the average task index values ​​corresponding to the other schools in the target resolution dimension;

[0046] The average task indicator value is set as the task indicator value of the target school in the target resolution dimension.

[0047] Furthermore, the step of constructing a task planning scheme for the target school according to the task planning schemes corresponding to the other schools to complete the task planning for the target school also includes:

[0048] According to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension;

[0049] Performing majority screening on the task indicator values ​​corresponding to the other schools in the target analysis dimension, to obtain the majority indicator values ​​corresponding to the other schools in the target analysis dimension;

[0050] The majority index value is set as the task index value of the target school in the target resolution dimension.

[0051] In order to solve the above technical problems, the embodiment of the present application also provides a service planning device, which adopts the following technical solution:

[0052] A service planning device, comprising:

[0053] A location information acquisition module is used to obtain the location information of the target school;

[0054] A multi-dimensional feature data acquisition module, used to acquire multi-dimensional feature data that has an impact on task planning for the target school;

[0055] A category information prediction module, used to input the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and output the category information of the target school after prediction;

[0056] A school screening module of the same category is used to screen out other schools belonging to the same category as the target school from historical stock data through the category information;

[0057] A task reference planning scheme acquisition module is used to obtain the task planning schemes corresponding to the other schools respectively;

[0058] The task target planning scheme construction module is used to construct the task planning scheme of the target school according to the task planning schemes corresponding to the other schools, so as to complete the task planning for the target school.

[0059] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0060] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the above-mentioned service planning method when executing the computer-readable instructions.

[0061] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0062] A computer-readable storage medium stores computer-readable instructions, which implement the steps of the service planning method described above when executed by a processor.

[0063] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0064] The business planning method described in the embodiment of the present application obtains the location information of the target school; obtains multidimensional feature data that has an impact on the task planning of the target school; inputs the location information and the multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputs the category information of the target school after prediction; selects other schools that belong to the same category as the target school from the historical stock data through the category information; obtains the task planning schemes corresponding to the other schools; and constructs the task planning scheme of the target school according to the task planning schemes corresponding to the other schools to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method described can determine the school category according to the geographical location information and multidimensional social environmental factors of the target school, and construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category, which can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0066] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0067] Figure 2 is a flow chart of an embodiment of a business planning method according to the present application;

[0068] Figure 3 yes Figure 2 A flowchart of a specific embodiment of pre-training the school category prediction model before step 203 is shown;

[0069] Figure 4 yes Figure 3 A flowchart of a specific embodiment of preprocessing the model training data in step 301 is shown;

[0070] Figure 5 yes Figure 3 A flowchart of a specific embodiment of step 302 is shown;

[0071] Figure 6 yes Figure 5 A flowchart of a specific embodiment of step 503 is shown;

[0072] Figure 7 yes Figure 2 A flowchart of a specific embodiment of step 203 is shown;

[0073] Figure 8 yes Figure 2 A flowchart of a specific embodiment of step 206 is shown;

[0074] Fig. 9 yes Figure 2 A flowchart of another specific embodiment of step 206 is shown;

[0075] Fig.10 is a schematic diagram of the structure of an embodiment of a service planning device according to the present application;

[0076] Fig.11 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0078] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0079] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0080] like Figure 1As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0081] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0082] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0083] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0084] It should be noted that the service planning method provided in the embodiment of the present application is generally executed by a terminal device, and accordingly, the service planning device is generally arranged in the terminal device.

[0085] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.

[0086] Continue to refer Figure 2 , shows a flow chart of an embodiment of a service planning method according to the present application. The service planning method comprises the following steps:

[0087] Step 201, obtaining the location information of the target school;

[0088] Specifically, the location information of the target school includes information such as longitude, latitude and altitude obtained by satellite positioning equipment and altitude measuring equipment.

[0089] By obtaining the location information of the target school, business planning can be carried out at the level of a larger geographical area, avoiding the problem of fewer reference objects for business planning in a small area.

[0090] Step 202, obtaining multi-dimensional feature data that has an impact on the task planning of the target school, wherein the multi-dimensional feature data includes the terrain characteristics, climate characteristics, vegetation coverage, population density information, average income level, housing prices, number of residential areas, traffic conditions, business district information, medical-related facilities, school establishment time, registered capital, teacher quality, tuition information, external evaluation, etc. of the area where the school is located.

[0091] By obtaining multi-dimensional feature data that affects the task planning of the target school, business plan planning can be carried out in combination with the multi-dimensional impact characteristics, ensuring that the influencing factors considered in business plan planning are more comprehensive, thereby achieving the scientificity and rationality of the final generated business plan.

[0092] Step 203, inputting the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and outputting the category information of the target school after prediction;

[0093] Specifically, the category information of the target school is predicted based on the geographical location information and multi-dimensional social environmental factors of the target school, ensuring that the task planning plan of the target school can be constructed in the future based on the task planning plans of all schools in the school category. For example, in the business planning of school insurance pricing and setting terms, by predicting the category information of the target school, a school insurance pricing and term planning plan is constructed based on the school insurance pricing and term planning plans of other schools in the category information. This can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance underwriting plans for students in different regions based on schools, which is more scientific and reasonable.

[0094] Step 204, filtering out other schools belonging to the same category as the target school from the historical stock data using the category information;

[0095] In this embodiment, it should be understood that as the school category prediction model is gradually put into use, the historical stock data will be incrementally increased based on the original training data. That is, after each prediction, the target school will be added as incremental information to the previous school category data to ensure that the prediction results of the school category prediction model become more and more mature and accurate.

[0096] Step 205, obtaining the task planning solutions corresponding to the other schools respectively;

[0097] In this embodiment, taking school insurance as an example, it should be understood that the task planning scheme includes the insurance pricing information, insurance amount information corresponding to each accident risk item in the school insurance, and compensation clause information corresponding to the accident risk event.

[0098] Step 206, constructing a task planning plan for the target school according to the task planning plans corresponding to the other schools, so as to complete the task planning for the target school.

[0099] In this embodiment, by obtaining the location information of the target school; obtaining multidimensional feature data that has an impact on the task planning of the target school; inputting the location information and the multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputting the category information of the target school after prediction; filtering out other schools belonging to the same category as the target school from the historical stock data through the category information; obtaining the task planning schemes corresponding to the other schools; and constructing the task planning scheme of the target school according to the task planning schemes corresponding to the other schools, so as to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environment factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category, which can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0100] Continue to refer Figure 3 In some optional implementations, a step of pre-training the school category prediction model is also included before step 203. Figure 3 yes Figure 2 The flowchart of a specific embodiment of pre-training the school category prediction model before step 203 shown includes the following steps:

[0101] Step 301, obtaining model training data and preprocessing the model training data, wherein the model training data includes location information of a batch of schools collected in advance and the multidimensional feature data that has an impact on task planning for each school in the batch of schools;

[0102] Step 302: input the preprocessed model training data into the school category prediction model to be trained, pre-train the school category prediction model to be trained, and obtain a pre-trained school category prediction model.

[0103] By pre-training the school category prediction model to be trained, a pre-trained school category prediction model is obtained, which ensures that when the school category prediction is actually performed on the target school in the future, the output prediction category is the school category divided on the basis of the pre-training, so that the prediction result is based on a basis and is more scientific.

[0104] Continue to refer Figure 4 , in some optional implementations, Figure 4 yes Figure 3 The flowchart of a specific embodiment of preprocessing the model training data in step 301 includes the following steps:

[0105] Step 401, obtaining the distinguishing identification information of each school in the batch of schools, wherein the distinguishing identification information includes school name information or school distinguishing code information;

[0106] Step 402, based on the distinguishing identification information, filter out the location information and the multi-dimensional feature data corresponding to the same school from the model training data as a screening result;

[0107] Step 403: Based on the screening result, generate group training data corresponding to each school in the batch of schools to complete the preprocessing of the model training data.

[0108] By preprocessing the model training data and generating group training data corresponding to each school in the batch of schools, the standardization of the input data is ensured when pre-training the school category prediction model, and random and chaotic input of training data is avoided. At the same time, standardized input can not only improve the pre-training efficiency of the model, but also minimize the error rate of group data pairing during model training.

[0109] Continue to refer Figure 5 , in some optional implementations, Figure 5 yes Figure 3 The flowchart of a specific embodiment of step 302 shown includes the following steps:

[0110] Step 501, obtaining the importance coefficient pre-set according to the position information, and the importance coefficients respectively set for the multi-dimensional features corresponding to the multi-dimensional feature data;

[0111] Step 502, using a preset comprehensive representation distance algorithm:

[0112]

[0113] Calculate the comprehensive representation distance between two schools in the batch of schools, D s represents the comprehensive characterization distance,

[0114] In the formula, ω x ·|x i -x j |+ω y ·|y i -y j |+ω z ·|z i -z j | represents the location distance value of schools numbered i and j, x represents longitude, y represents latitude, z represents altitude, ω x ,ω y and ω z They represent the longitude importance coefficient, latitude importance coefficient and altitude importance coefficient respectively.

[0115] In the formula, represents the total distance value of the characteristics of schools numbered i and j in the k dimensions, k represents the number of dimensions of the multi-dimensional feature, |a ik -a jk | represents the characteristic distance value of schools numbered i and j in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension;

[0116] Specifically, you can set ω separately x +ω y +ω z =1,ω1+ω2+……+ω k-1 +ω k =1, or you can set ω comprehensively x +ω y +ω z +(ω1+ω2+……+ω k-1 +ω k )=1.

[0117] Step 503, clustering the batch of schools according to the comprehensive representation distance between every two schools in the batch of schools and the preset number of clustering clusters, to obtain school categories equal to the number of clustering clusters;

[0118] Specifically, in theory, the purpose of clustering is to cluster the schools in the batch of schools with smaller comprehensive representation distances between each other as a category. The number of clusters can be freely set according to actual business needs. For example, if an insurance company provides 10 school insurance plans with different insurance prices, the number of clusters can be set to 10.

[0119] Step 504, performing average calculation based on the location information of all schools included in each cluster and the multidimensional feature data, to obtain the location information of the proposed center point of each cluster and the multidimensional feature data;

[0120] Specifically, based on the location information of all schools contained in each cluster and the multidimensional feature data, an average value is calculated to obtain the location information of the proposed center point of each cluster and the multidimensional feature data. By proposing the center point of each cluster, when the school category of the target school is subsequently predicted, the comprehensive representation distance between the target school and each proposed center point is directly calculated, and the cluster (school category) to which the target school belongs can be predicted, thereby improving the model prediction efficiency.

[0121] Step 505 , setting the location information of the proposed center point of each cluster and the multi-dimensional feature data as category identification data of each school category, and completing the pre-training of the school category prediction model to be trained.

[0122] By pre-training the school category prediction model, the location information of the proposed center point of each cluster and the multi-dimensional feature data are obtained. When performing actual predictions later, it is only necessary to calculate the comprehensive representation distance between the target school and each proposed center point to predict the cluster (school category) to which the target school belongs, thereby improving the model prediction efficiency.

[0123] Continue to refer Figure 6 , in some optional implementations, Figure 6 yes Figure 5 The flowchart of a specific embodiment of step 503 shown includes the following steps:

[0124] Step 601, taking the comprehensive representation distance between any two schools in the batch of schools and the preset number of clusters as clustering parameters;

[0125] Step 602: clustering the batch of schools using a K-means clustering algorithm to obtain school categories equal in number to the number of clusters.

[0126] Continue to refer Figure 7 , in some optional implementations, Figure 7 yes Figure 2 The flowchart of a specific embodiment of step 203 shown includes the following steps:

[0127] Step 701, obtaining category identification data of each school category;

[0128] Step 702, identifying the location information of the proposed center point of each cluster and the multi-dimensional feature data according to the category identification data of each school category;

[0129] Step 703, using a preset comprehensive representation distance algorithm:

[0130]

[0131] Calculate the comprehensive representation distance between the target school and the proposed center point of each cluster, D p represents the comprehensive characterization distance,

[0132] In the formula, x p ,y p and z p Together, they represent the location information of the target school. Specifically, x p Indicates the longitude of the target school, y p represents the latitude of the target school, z p represents the altitude of the target school, and correspondingly, x o ,y o and z o Together they represent the location information of the proposed center point of the current cluster. Specifically, x o Indicates the longitude of the target school, y o represents the latitude of the target school, z o represents the altitude of the target school, ω x ,ω y and ω z represent the longitude importance coefficient, the latitude importance coefficient and the altitude importance coefficient respectively,

[0133] In the formula, represents the total feature distance value between the target school and the proposed center point of the current cluster in the k dimensions, where k represents the number of dimensions of the multi-dimensional feature, |a pk -a ok | represents the characteristic distance value between the target school and the proposed center point of the current cluster in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension;

[0134] Step 704, based on the comprehensive representation distance between the target school and the proposed center point of each cluster, select the proposed center point with the smallest comprehensive representation distance with the target school as the target center point;

[0135] Step 705: Use the school category corresponding to the target center point as the category information of the target school and perform model output processing.

[0136] In fact, the category information of the target school is predicted based on the geographical location information and multi-dimensional social environmental factors of the target school, which ensures that the task planning plan of the target school can be constructed based on the task planning plans of all schools in the school category. For example, in the business planning of school insurance pricing and setting terms, by predicting the category information of the target school, the school insurance pricing and term planning plan of other schools in the category information is constructed. This can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance underwriting plans for students in different regions based on schools, which is more scientific and reasonable.

[0137] Continue to refer Figure 8 , in some optional implementations, Figure 8 yes Figure 2 The flowchart of a specific embodiment of step 206 shown includes the following steps:

[0138] Step 801, according to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension;

[0139] Step 802, averaging the task indicator values ​​corresponding to the other schools in the target parsing dimension to obtain the average task indicator value corresponding to the other schools in the target parsing dimension;

[0140] Step 803: Set the average task indicator value as the task indicator value of the target school in the target resolution dimension.

[0141] In essence, taking the above-mentioned school insurance as an example, assuming that the corresponding insured amounts of other schools of the same category range from 150 yuan to 180 yuan, by finding the total average, for example: the average value is 170 yuan, then the average value is set as the insured amount corresponding to the target school, and the insurance plan planning of the school insurance is transferred from the student level to the school level, which not only reduces the complexity of the school insurance plan planning, but also improves the efficiency of the school insurance plan planning.

[0142] Continue to refer Fig. 9 , in some optional implementations, Fig. 9 yes Figure 2 The flowchart of another specific embodiment of step 206 shown includes the following steps:

[0143] Step 901, according to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension;

[0144] Step 902, performing majority screening on the task indicator values ​​corresponding to the other schools in the target parsing dimension, and obtaining the majority indicator values ​​corresponding to the other schools in the target parsing dimension;

[0145] Step 903, setting the majority index value as the task index value of the target school in the target resolution dimension.

[0146] In essence, taking the above-mentioned school insurance as an example, assuming that the corresponding insured amount of other schools of the same category ranges from 150 yuan to 180 yuan, by screening the mode value, for example: the mode value is 170 yuan, then the average value is set as the insured amount corresponding to the target school, the mode value, assuming that there are 100 other schools of the same category, of which 70 have a corresponding insured amount of 170 yuan. Obviously, 170 yuan is the mode value, which transfers the insurance plan planning of school insurance from the student level to the school level, which not only reduces the complexity of school insurance plan planning, but also improves the efficiency of school insurance plan planning.

[0147] Among them, the preset target analysis dimension is set according to the task planning plan corresponding to the target school. Specifically, if the task planning plan corresponding to the target school only needs to fill in one task indicator value, that is, only the insured amount needs to be predicted in the school insurance, then arbitrarily select one method from the two task indicator value determination methods to obtain the task indicator value of the target analysis dimension; if the task planning plan corresponding to the target school needs to fill in multiple different types of task indicator values, it can be understood that it is necessary to predict multiple indicator values ​​in the school insurance, then flexibly select a determination method from the two task indicator value determination methods to obtain multiple different types of task indicator values.

[0148] This application obtains the location information of the target school; obtains multidimensional feature data that has an impact on the task planning of the target school; inputs the location information and multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputs the category information of the target school after prediction; selects other schools that belong to the same category as the target school from the historical stock data through the category information; obtains the task planning schemes corresponding to the other schools; and constructs the task planning scheme of the target school according to the task planning schemes corresponding to the other schools to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environmental factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category. It can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0149] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0150] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0151] In the embodiment of the present application, by obtaining the location information of the target school; obtaining multidimensional feature data that has an impact on the task planning of the target school; inputting the location information and the multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputting the category information of the target school after prediction; filtering out other schools belonging to the same category as the target school from the historical stock data through the category information; obtaining the task planning schemes corresponding to the other schools; and constructing the task planning scheme of the target school according to the task planning schemes corresponding to the other schools, so as to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environmental factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category, which can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0152] Further references Fig.10 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a service planning device, and the embodiment of the device is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0153] like Fig.10 As shown, the business planning device 10 described in this embodiment includes: a location information acquisition module 10a, a multi-dimensional feature data acquisition module 10b, a category information prediction module 10c, a same category school screening module 10d, a task reference planning scheme acquisition module 10e and a task target planning scheme construction module 10f. Among them:

[0154] A location information acquisition module 10a is used to acquire the location information of a target school;

[0155] A multi-dimensional feature data acquisition module 10b, used to acquire multi-dimensional feature data that has an impact on the task planning of the target school;

[0156] A category information prediction module 10c is used to input the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and output the category information of the target school after prediction;

[0157] A school screening module 10d of the same category is used to screen out other schools of the same category as the target school from the historical stock data according to the category information;

[0158] A task reference planning scheme acquisition module 10e is used to acquire the task planning schemes corresponding to the other schools respectively;

[0159] The task target planning scheme building module 10f is used to build a task planning scheme for the target school according to the task planning schemes corresponding to the other schools, so as to complete the task planning for the target school.

[0160] This application obtains the location information of the target school; obtains multidimensional feature data that has an impact on the task planning of the target school; inputs the location information and multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputs the category information of the target school after prediction; selects other schools that belong to the same category as the target school from the historical stock data through the category information; obtains the task planning schemes corresponding to the other schools; and constructs the task planning scheme of the target school according to the task planning schemes corresponding to the other schools to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environmental factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category. It can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0161] Those 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 computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0162] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0163] To solve the above technical problems, the present application also provides a computer device. Fig.11 , Fig.11 This is a basic structural block diagram of the computer device in this embodiment.

[0164] The computer device 11 includes a memory 11a, a processor 11b, and a network interface 11c which are interconnected through a system bus. It should be noted that: Fig.11 Only a computer device 11 having a component memory 11a, a processor 11b, and a network interface 11c is shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital processor (DSP), an embedded device, etc.

[0165] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0166] The memory 11a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11a can be an internal storage unit of the computer device 11, such as a hard disk or memory of the computer device 11. In other embodiments, the memory 11a can also be an external storage device of the computer device 11, such as a plug-in hard disk equipped on the computer device 11, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 11a can also include both the internal storage unit of the computer device 11 and its external storage device. In this embodiment, the memory 11a is generally used to store the operating system and various application software installed on the computer device 11, such as a computer-readable instruction of a business planning method, etc. In addition, the memory 11a can also be used to temporarily store various types of data that have been output or are to be output.

[0167] The processor 11b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 11b is generally used to control the overall operation of the computer device 11. In this embodiment, the processor 11b is used to run computer-readable instructions stored in the memory 11a or process data, such as computer-readable instructions for running the business planning method.

[0168] The network interface 11c may include a wireless network interface or a wired network interface. The network interface 11c is generally used to establish a communication connection between the computer device 11 and other electronic devices.

[0169] The computer device proposed in this embodiment belongs to the field of financial technology and is applied to the scenario of insurance plan adjustment. This application obtains the location information of the target school; obtains the multidimensional feature data that has an impact on the task planning of the target school; inputs the location information and the multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputs the category information of the target school after prediction; selects other schools belonging to the same category as the target school from the historical stock data through the category information; obtains the task planning schemes corresponding to the other schools; and constructs the task planning scheme of the target school according to the task planning schemes corresponding to the other schools to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environment factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category, which can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0170] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by a processor to enable the processor to perform the steps of the business planning method as described above.

[0171] The computer-readable storage medium proposed in this embodiment belongs to the field of financial technology and is applied to the scenario of insurance plan adjustment. This application obtains the location information of the target school; obtains the multidimensional feature data that has an impact on the task planning of the target school; inputs the location information and the multidimensional feature data as a set of prediction data into the pre-trained school category prediction model, and outputs the category information of the target school after prediction; selects other schools belonging to the same category as the target school from the historical stock data through the category information; obtains the task planning schemes corresponding to the other schools; and constructs the task planning scheme of the target school according to the task planning schemes corresponding to the other schools to complete the task planning of the target school. Especially in the scenario of school insurance pricing and clause setting, the task planning method can be used to determine the school category according to the geographical location information and multidimensional social environment factors of the target school, and to construct the school insurance pricing and clause planning scheme according to the school insurance pricing and setting clauses of all schools in the school category, which can fully combine the actual living standards and regional differences of the region, and flexibly generate school insurance plans for students in different regions based on schools, which is more scientific and reasonable.

[0172] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0173] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A business planning method, characterized in that: The steps include: Get the location information of the target school; Acquire multidimensional feature data that has an impact on task planning for the target school; Input the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and output the category information of the target school after prediction; Using the category information, filter out other schools belonging to the same category as the target school from historical stock data; Obtaining task planning solutions corresponding to the other schools respectively; According to the task planning plans corresponding to the other schools, a task planning plan for the target school is constructed to complete the task planning for the target school.

2. The service planning method according to claim 1, characterized in that: Before executing the step of inputting the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and outputting the category information of the target school after prediction, the method further includes: Acquire model training data and preprocess the model training data, wherein the model training data includes pre-collected location information of a batch of schools and the multidimensional feature data that has an impact on task planning for each school in the batch of schools; The preprocessed model training data is input into the school category prediction model to be trained, and the school category prediction model to be trained is pre-trained to obtain a pre-trained school category prediction model.

3. The service planning method according to claim 2, characterized in that: The step of preprocessing the model training data specifically includes: Obtaining distinguishing identification information of each school in the batch of schools, wherein the distinguishing identification information includes school name information or school distinguishing code information; According to the distinguishing identification information, the location information and the multi-dimensional feature data corresponding to the same school are filtered out from the model training data as a filtering result; Based on the screening results, group training data corresponding to each school in the batch of schools is generated to complete the preprocessing of the model training data.

4. The service planning method according to claim 2, characterized in that: The step of pre-training the school category prediction model to be trained specifically includes: Obtaining the importance coefficients pre-set according to the position information and the importance coefficients respectively set for the multi-dimensional features corresponding to the multi-dimensional feature data; Using the preset comprehensive representation distance algorithm: Calculate the comprehensive representation distance between two schools in the batch of schools, D s represents the comprehensive characterization distance, In the formula, ω x ·x i -x j +ω y ·y i -y j +ω z ·z i -z j | represents the location distance value of schools numbered i and j, x represents longitude, y represents latitude, z represents altitude, ω x ,ω y and ω z They represent the longitude importance coefficient, latitude importance coefficient and altitude importance coefficient respectively. In the formula, represents the total distance value of the characteristics of schools numbered i and j in the k dimensions, k represents the number of dimensions of the multi-dimensional feature, |a ik -a jk | represents the characteristic distance value of schools numbered i and j in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension; Clustering the batch of schools according to the comprehensive representation distance between any two schools in the batch of schools and the preset number of clustering clusters to obtain school categories equal to the number of clustering clusters; Calculate the average value based on the location information of all schools included in each cluster and the multidimensional feature data to obtain the location information of the proposed center point of each cluster and the multidimensional feature data; The location information of the proposed center point of each cluster and the multi-dimensional feature data are set as the category identification data of each school category, so as to complete the pre-training of the school category prediction model to be trained.

5. The service planning method according to claim 4, characterized in that: The step of clustering the batch of schools according to the comprehensive representation distance between any two schools in the batch of schools and the preset number of clustering clusters to obtain the same number of school categories as the number of clustering clusters specifically includes: The comprehensive representation distance between any two schools in the batch of schools and the preset number of clusters are used as clustering parameters; The batch of schools is clustered using a K-means clustering algorithm to obtain school categories equal in number to the number of clusters.

6. The service planning method according to claim 4, characterized in that: The step of inputting the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and outputting the category information of the target school after prediction, specifically includes: Get category identification data for each school category; According to the category identification data of each school category, identifying the location information of the proposed center point of each cluster and the multi-dimensional feature data; Using the preset comprehensive representation distance algorithm: Calculate the comprehensive representation distance between the target school and the proposed center point of each cluster, D p represents the comprehensive characterization distance, In the formula, x p ,y p and z p Together, they represent the location information of the target school. Specifically, x p Indicates the longitude of the target school, y p represents the latitude of the target school, z p represents the altitude of the target school, and correspondingly, x o ,y o and z o Together they represent the location information of the proposed center point of the current cluster. Specifically, x o Indicates the longitude of the target school, y o represents the latitude of the target school, z o represents the altitude of the target school, ω x ,ω y and ω z represent the longitude importance coefficient, the latitude importance coefficient and the altitude importance coefficient respectively, In the formula, represents the total feature distance value between the target school and the proposed center point of the current cluster in the k dimensions, k represents the number of dimensions of the multi-dimensional feature, a pk -a ok | represents the characteristic distance value between the target school and the proposed center point of the current cluster in the kth dimension, ω k Represents the importance coefficient corresponding to the feature of the kth dimension; According to the comprehensive representation distance between the target school and the proposed center point of each cluster, the proposed center point with the smallest comprehensive representation distance to the target school is selected as the target center point; The school category corresponding to the target center point is used as the category information of the target school, and model output processing is performed.

7. The service planning method according to claim 1, characterized in that: The step of constructing a task planning scheme for the target school according to the task planning schemes corresponding to the other schools to complete the task planning for the target school includes: According to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension; The task index values ​​corresponding to the other schools in the target resolution dimension are averaged to obtain the average task index values ​​corresponding to the other schools in the target resolution dimension; The average task indicator value is set as the task indicator value of the target school in the target resolution dimension.

8. The service planning method according to claim 1, characterized in that: The step of constructing a task planning scheme for the target school according to the task planning schemes corresponding to the other schools to complete the task planning for the target school also includes: According to the preset target analysis dimension, the task indicator value of the task planning schemes corresponding to the other schools is analyzed to obtain the task indicator values ​​corresponding to the other schools in the target analysis dimension; Performing majority screening on the task indicator values ​​corresponding to the other schools in the target analysis dimension, to obtain the majority indicator values ​​corresponding to the other schools in the target analysis dimension; The majority index value is set as the task index value of the target school in the target resolution dimension.

9. A service planning device, characterized in that: include: A location information acquisition module is used to obtain the location information of the target school; A multi-dimensional feature data acquisition module, used to acquire multi-dimensional feature data that has an impact on task planning for the target school; A category information prediction module, used to input the location information and the multi-dimensional feature data as a set of prediction data into a pre-trained school category prediction model, and output the category information of the target school after prediction; A school screening module of the same category is used to screen out other schools of the same category as the target school from the historical stock data through the category information; A task reference planning scheme acquisition module is used to obtain the task planning schemes corresponding to the other schools respectively; The task target planning scheme construction module is used to construct the task planning scheme of the target school according to the task planning schemes corresponding to the other schools, so as to complete the task planning for the target school.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the service planning method according to any one of claims 1 to 8 when executing the computer-readable instructions.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the service planning method according to any one of claims 1 to 8 are implemented.

Images