Resource automatic allocation method and device, electronic device and computer readable medium

Abstract

A method, device and electronic device for automatic resource allocation, wherein the method comprises: evaluating and grading resource undertakers; scoring current access resources; and automatically allocating the access resources to resource undertakers of corresponding levels according to the scores of the access resources. The present invention grades resource undertakers, scores visiting users, and uses an intelligent allocation algorithm to automatically allocate the scored users to resource undertakers of corresponding levels for one-to-one service, thereby maximizing allocation efficiency, ensuring that high-quality users can be matched with resource undertakers with strong capabilities, increasing the probability of user conversion, improving user experience and increasing the revenue of educational institutions.

Description

Technical Field

[0001] The present invention belongs to the technical field of machine learning, and in particular relates to a method, device, electronic device and computer-readable medium for automatic resource allocation. Background Art

[0002] With the development of modern information technology and the needs of the education market, online education, as a new educational concept, is being promoted and popularized. In order to attract more users to buy online education products, educational institutions will first promote online education products through advertisements and other forms. When users browse educational products through advertisements, educational institutions will arrange staff from different seats to answer one-on-one questions to enhance users' willingness to buy.

[0003] In the prior art, sales agents allocate access resources by randomly accessing the staff's phones through a program-controlled device. Since each staff member has different abilities, this method of allocating access cannot maximize the efficiency of the entire system. Therefore, how to automatically allocate corresponding resources by setting an intelligent matching algorithm in the program-controlled device to maximize benefits has become a technical problem that urgently needs to be solved. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] The present invention aims to solve the technical problem of how to automatically allocate resources to maximize benefits.

[0006] (II) Technical solution

[0007] In order to solve the above technical problems, one aspect of the present invention provides a method for automatic resource allocation, comprising:

[0008] Evaluate and grade resource undertakers;

[0009] Score the current access resources;

[0010] According to the score of the access resource, the access resource is automatically allocated to a resource undertaker of a corresponding level.

[0011] According to a preferred embodiment of the present invention, the identity information and behavior data of the resource undertaker are input into the trained first scoring model, and the score of the resource undertaker is output;

[0012] Set the scoring range corresponding to each level of resource undertaker;

[0013] A corresponding level is set for the resource undertaker according to the score of the resource undertaker.

[0014] According to a preferred embodiment of the present invention, the scoring of the current access resources includes:

[0015] The identity information and behavior data of the current user in the access resource are input into the trained second scoring model, and the score of the user is output.

[0016] According to a preferred embodiment of the present invention, automatically allocating the access resource to a resource undertaker of a corresponding level according to the score of the access resource includes:

[0017] Input the user's score into a pre-trained allocation model to obtain the resource undertaker level assigned to the user;

[0018] A resource undertaker who is idle is selected from the resource undertaker level to serve the user.

[0019] According to a preferred embodiment of the present invention, the step of inputting the user's score into a pre-trained allocation model to obtain the resource undertaker level allocated to the user further includes:

[0020] Setting an initial average score for each level based on historical data, and setting a user number threshold for each level;

[0021] Obtain the current user's score, and calculate the difference between the score and the average score of each level;

[0022] The current user is assigned to the level with the smallest difference.

[0023] According to a preferred embodiment of the present invention, allocating the current user to the level with the smallest difference further comprises:

[0024] Real-time detection of whether the number of users currently included in each level is lower than the user number threshold;

[0025] If a level containing a number of users below the user number threshold is detected, the difference between the current user score and the average score of each level below the user number threshold is calculated, and the current user is assigned to the level with the smallest difference among the levels below the threshold.

[0026] According to a preferred embodiment of the present invention, after allocating the current user to the level with the smallest difference, the method further comprises:

[0027] Calculate the average of user ratings in each level;

[0028] Sort the levels in descending order according to the average scores of users at all levels;

[0029] Get the next user's score, calculate the difference between the user's score and the average score of each level after sorting, and assign the user to the corresponding level according to the difference until all users are assigned.

[0030] According to a preferred embodiment of the present invention, the user number threshold is a preset value where the number of users at each level is not less than the average value of the total number of users at all levels.

[0031] A second aspect of the present invention provides an automatic resource allocation device, comprising:

[0032] Resource undertaker grading module, used to evaluate and grade resource undertakers;

[0033] Access resource scoring module, used to score current access resources;

[0034] The automatic resource allocation module is used to automatically allocate the access resources to resource undertakers of corresponding levels according to the scores of the access resources.

[0035] A third aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer executable program, and when the computer program is executed by the processor, the processor executes any one of the above-mentioned automatic resource allocation methods.

[0036] A fourth aspect of the present invention further proposes a computer-readable medium storing a computer-executable program, wherein when the computer-executable program is executed, any of the above-mentioned automatic resource allocation methods is implemented.

[0037] A fifth aspect of the present invention further proposes a computer executable program, which, when executed, implements any of the above-mentioned automatic resource allocation methods.

[0038] (III) Beneficial effects

[0039] The present invention grades resource undertakers, scores visiting users, and uses an intelligent allocation algorithm to automatically assign the scored users to resource undertakers of corresponding levels for one-to-one service, thereby maximizing allocation efficiency, ensuring that high-quality users can be matched with resource undertakers with strong capabilities, increasing the probability of user conversion, improving user experience, and increasing the revenue of educational institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a schematic diagram of an application scenario of an automatic resource allocation method provided by an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of a flow chart of a method for automatic resource allocation provided by an embodiment of the present invention;

[0042] Figure 3 It is a schematic diagram of a real-time allocation algorithm flow chart provided by an embodiment of the present invention;

[0043] Figure 4 It is a schematic diagram of an automatic resource allocation device provided by an embodiment of the present invention;

[0044] Figure 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention;

[0045] Figure 6 is a schematic diagram of a computer-readable recording medium provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In the process of introducing specific embodiments, the detailed description of the structure, performance, effect or other characteristics is to enable those skilled in the art to fully understand the embodiments. However, it does not exclude that those skilled in the art can implement the present invention with a technical solution that does not contain the above-mentioned structure, performance, effect or other characteristics under certain circumstances.

[0047] The flowchart in the accompanying drawings is only an exemplary process demonstration, and does not mean that the solution of the present invention must include all the contents, operations and steps in the flowchart, nor does it mean that it must be executed in the order shown in the figure. For example, some operations / steps in the flowchart can be decomposed, some operations / steps can be combined or partially combined, etc. The execution order shown in the flowchart can be changed according to actual conditions without departing from the main purpose of the present invention.

[0048] Frames in the attached figure Figure 1 Generally, it refers to functional entities, which do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processing unit devices and / or microcontroller devices.

[0049] The same reference numerals in the drawings represent the same or similar elements, components or parts, so the repeated description of the same or similar elements, components or parts may be omitted below. It should also be understood that although the first, second, third and other attributives representing the numbers may be used herein to describe various devices, elements, components or parts, these devices, elements, components or parts should not be limited by these attributives. In other words, these attributives are only used to distinguish one from another. For example, the first device may also be called the second device, but it does not deviate from the essential technical solution of the present invention. In addition, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0050] Figure 1 This is a schematic diagram of an application scenario of an automatic resource allocation method provided by an embodiment of the present invention. The present invention takes an educational institution as an example. The resource recipients in the embodiment of the present invention include but are not limited to sales personnel of the educational institution, and the access resources include but are not limited to visiting users, user telephones, user network requests, etc. Figure 1 As shown, the background server will pre-rate the sales staff of the educational institution based on their identity information and behavior data. The higher the level, the stronger the sales ability. When the user logs in to the client through the educational institution's APP, the client will obtain the user information. While the user is browsing educational products, the client will send the obtained user behavior data to the background server to rate the user. The rating can be set with different meanings according to different situations. It can indicate the user's willingness to buy or the quality of the user. The higher the score, the stronger the user's willingness to buy or the better the user quality. At this time, the background server automatically assigns a salesperson of the corresponding level to the user according to the intelligent allocation algorithm, and the salesperson provides one-to-one service to the user to increase the probability of the user purchasing educational products.

[0051] The intelligent allocation algorithm automatically assigns sales personnel of different levels to users with different scores, ensuring that sales personnel of each level can be assigned corresponding users. This prevents some sales personnel from being too busy while others are idle, thus improving resource utilization.

[0052] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0053] Figure 2 The present invention provides a flowchart of an automatic resource allocation method according to an embodiment of the present invention. The method can automatically allocate appropriate resource undertakers to accessing users.

[0054] like Figure 2 As shown, the method includes:

[0055] S101. Evaluate and grade resource recipients.

[0056] In some embodiments, the server stores information about each salesperson and recent behavior data of the salesperson, and scores the salesperson based on their different performance indicators by inputting the salesperson's information and behavior data into a trained first scoring model.

[0057] After getting the score of each salesperson, all salespeople are graded. According to the overall score, the score range is set for each level, so that the number of salespeople in each level is not much different. For example, there are 100 salespeople in total, divided into 5 levels with scores between 0 and 1. According to the scoring results, the score [0,0.3) is divided into the 5th level, the score [0.3,0.5) is divided into the 4th level, the score [0.5,0.7) is divided into the 3rd level, the score [0.7,0.85) is divided into the 2nd level, and the score [0.85,1] is divided into the 1st level, so as to ensure that the number of salespeople in each level is about 20. The number of grades and the score range of each level can be adjusted at any time according to the salesperson.

[0058] S102: Score the current access resources.

[0059] In some embodiments, the method for scoring visiting users is similar to the method for scoring sales personnel in the above embodiments. After the user logs in to the education institution client, the server will obtain the user's identity information after the user authorizes, such as the user's age, education, location, occupation and income status, etc. When the user is browsing educational products, the server will collect the user's behavior data, such as the time the user stays on a certain education product page, the number of times a certain education product is clicked, etc. The user's identity information and behavior data are input into the trained second scoring model to obtain the user's score. The higher the score, the better the user quality and the higher the willingness to buy.

[0060] S103. Automatically assigning the access resource to a resource undertaker of a corresponding level according to the score of the access resource.

[0061] In some embodiments, after a user visits an educational institution, it is necessary to calculate the user score in real time and assign corresponding sales personnel to the user. Since the number of users visiting the educational institution every day is very large, it is impossible to estimate in advance the overall score of all users every day. It is possible that the proportion of high-scoring customers on a certain day is large, or the proportion of low-scoring customers is large. In this case, it is impossible to assign absolutely high-scoring customers to high-scoring sales personnel, or assign absolutely low-scoring customers to low-scoring sales personnel based on a certain score. If most high-scoring users are assigned to sales personnel at the same level, the sales personnel at that level will be too busy and unable to meet user needs, resulting in customer loss, while sales personnel at other levels will be idle, which not only has low resource utilization but also affects the revenue of the educational institution.

[0062] In order to solve the above problem, the embodiment of the present invention uses a real-time allocation algorithm to evenly allocate new users to sales personnel at all levels in real time, so that the number of users allocated to sales personnel at each level is basically the same.

[0063] The user's score can be input into a pre-trained allocation model to obtain the level of resource undertaker assigned to the user. The allocation model can be obtained by training a machine learning model using a real-time allocation algorithm based on historical users as training samples, or by directly substituting the real-time allocation algorithm into an ordinary model for use as an allocation model.

[0064] Figure 3 FIG. 1 is a flow chart of a real-time allocation algorithm provided by an embodiment of the present invention. Figure 3 As shown, the real-time allocation algorithm includes the following steps:

[0065] S1031. Treat each salesperson level as a set, and set an initial average score for each set. The initial average score of each set is the same. The initial average score can be determined by historical experience, such as the average score of all users in the past few days, to ensure that the gap with the score of the current user is small.

[0066] S1032. Set a user number threshold for each collection. The user number of each collection can be set to a preset value that cannot be lower than the average value of the total number of users in all collections. The preset value can be, for example, 1%, 5%, etc. For collections below the threshold, users will be preferentially allocated to the collection, thereby ensuring that the number of users in each collection is not too different from that of other collections.

[0067] S1033. Obtain the current user's score, calculate the difference between the user's score and the average score of each set, and assign the user to the set with the smallest difference, that is, assign the user to the set whose average score is closest to that of the set.

[0068] Preferably, assigning the current user to a corresponding set specifically includes the following steps:

[0069] S10331. Sort all sets in descending order according to their average scores.

[0070] S10332. Determine the number of sets that currently meet the requirements.

[0071] (1) When there is only one set, directly assign the current user to that set;

[0072] (2) When the number of sets is 2, assign the current user to the set that is closer to the average score;

[0073] (3) When the number of sets is greater than 2, determine the relationship between the current user's score and the maximum and minimum values ​​of the average score of each set. If the current user's score is greater than the maximum value of the average score, directly assign the user's score to the set with the smallest sequence number; if the current user's score is less than the minimum value of the average score, directly assign the user's score to the set with the largest sequence number; if the current user's score is between the maximum average score and the minimum average score, exclude the set with the maximum average score and the set with the minimum average score, and then re-execute according to steps S10331 and S10332. After allocating the users within a day, you will get sets with sequence numbers arranged from small to large, and the corresponding average scores are also arranged from small to large. Each time you obtain a user's score, you will execute steps S10331 and S10332 once.

[0074] For example, five salesperson levels are currently configured, corresponding to sets 1-5. An initial average score of 0.1 is set for each set, which is equivalent to an initial user. Sets 1-5 are represented as follows: 1: [1, 0.1], 2: [1, 0.1], 3: [1, 0.1], 4: [1, 0.1], 5: [1, 0.1], where the first value in [] indicates the number of users assigned to the set, and the second value indicates the current average score of the set. At the same time, it is set that the number of users in each set cannot be lower than 5% of the average of the total number of users in all sets.

[0075] When the first user with a score of 0.16 needs to be assigned, the five sets are first sorted according to step S10331. Since the average scores of the sets are the same at this time, the order remains unchanged. Then, according to step S10331, since 0.16 is greater than the average scores of all current sets, the user is assigned to set 1. At this time, set 1 is equivalent to containing two users, and the average score also becomes 0.13. The average of the total number of users in all sets is 1.2. Since the number of users in sets 2-5 is 1 at this time, which is lower than the set threshold, the second user will only be assigned to one of the sets 2-5. When the second user with a score of 0.2 needs to be assigned, the user is assigned to set 2 according to steps S10331 and S10332, and the algorithm steps are continued. For example, when it comes to the 30th assignment, the current set is sorted according to step S10331 as follows: 1: [10, 0.184000], 4: [5, 0.160000], 2: [6, 0.148333], 3: [5, 0.146000], 5: [8, 0.113750]. The score of the 30th user is 0.15. According to situation (3) of step S10332, 0.15 is between the maximum average value 0.184000 and the minimum average value 0.113750, so the corresponding sets 1 and 5 are excluded and the algorithm is re-sorted according to step S10331. Step S10331 sorts the remaining sets. At this time, there are 3 sets remaining. According to the situation (3) of step S10332, 0.15 is between the maximum average value 0.160000 and the minimum average value 0.146000, so the corresponding sets 4 and 3 are excluded. The remaining sets are sorted according to step S10331. At this time, there is 1 set remaining. According to the situation (1) of step S10332, the user is directly assigned to set 2. The results after 200 assignments are: 1: [46, 0.218913], 2: [46, 0.187826], 3: [32, 0.164063], 4: [43, 0.154884], 5: [38, 0.100000].

[0076] Tables 1 to 3 show the distribution data for different distribution numbers (the threshold is 1%):

[0077] Table 1

[0078] Number of people assigned: 200 Actual number of people assigned Actual average score Ideal number of people assigned Ideal average score Collection 1 41 0.20804878 40 0.23225000 Collection 2 46 0.16782609 40 0.20250000 Collection 3 39 0.17230769 40 0.17575000 Collection 4 39 0.15871795 40 0.14100000 Collection 5 40 0.13150000 40 0.09650000

[0079] Table 2

[0080] Number of people assigned: 1000 Actual number of people assigned Actual average score Ideal number of people assigned Ideal average score Collection 1 198 0.21994949 200 0.23485000 Collection 2 215 0.19345455 200 0.20500000 Collection 3 193 0.17155440 200 0.17580000 Collection 4 197 0.15000000 200 0.14210000 Collection 5 197 0.11472081 200 0.09660000

[0081] Table 3

[0082] Number of people assigned: 10000 Actual number of people assigned Actual average score Ideal number of people assigned Ideal average score Collection 1 1905 0.21994226 2000 0.23512000 Collection 2 1903 0.19980032 2000 0.20581000 Collection 3 2388 0.17522357 2000 0.17629000 Collection 4 1901 0.15013151 2000 0.14074000 Collection 5 1903 0.10677352 2000 0.09534500

[0083] It can be concluded from Tables 1 to 3 that the more people are assigned, the closer the average score of the set is to the ideal average score, and the number of users assigned to each set is not much different from the ideal number of users, which can achieve the goal of evenly assigning new users to sets of different levels.

[0084] In addition, setting different thresholds will also affect the allocation results. The larger the threshold is set, the closer the actual average score of each set is to the ideal average score, but the difference in the number of people allocated to each set will become larger. Therefore, corresponding indicators can be set according to different situations. For example, if you want to ensure that the number of users in each set is average, set the threshold to a smaller value. If you want to ensure that the user score allocated to each set is close to the ideal score, set a larger threshold.

[0085] You can also set different sales staff levels. When the number of sales staff is large enough, you can set multiple sales staff levels. The score range of each level of sales staff is smaller, so as to provide more accurate services to users with different scores.

[0086] S1034. Filter idle resource undertakers from each set to provide services for the user. After the user is assigned to the corresponding set, filter out the currently idle salespersons from the corresponding level of the set to provide one-to-one services to the user. The entire process from user login to salesperson assignment takes only a few milliseconds, which improves resource utilization.

[0087] The method in the embodiment of the present invention grades resource undertakers, scores visiting users, and uses an intelligent allocation algorithm to automatically assign the scored users to resource undertakers of corresponding levels for one-to-one service, thereby maximizing allocation efficiency, ensuring that high-quality users can be matched with resource undertakers with strong capabilities, increasing the probability of user conversion, improving user experience, and increasing the revenue of educational institutions.

[0088] Those skilled in the art will appreciate that all or part of the steps to implement the above embodiments are implemented as a program (computer program) executed by a computer data processing device. When the computer program is executed, the above method provided by the present invention can be implemented. Moreover, the computer program can be stored in a computer-readable storage medium, which can be a readable storage medium such as a disk, an optical disk, a ROM, a RAM, or a storage array composed of multiple storage media, such as a disk or a tape storage array. The storage medium is not limited to centralized storage, and it can also be distributed storage, such as cloud storage based on cloud computing.

[0089] The following describes an apparatus embodiment of the present invention, which can be used to execute a method embodiment of the present invention. The details described in the apparatus embodiment of the present invention should be regarded as supplementary to the above method embodiment; details not disclosed in the apparatus embodiment of the present invention can be implemented with reference to the above method embodiment.

[0090] Figure 4 is a schematic diagram of an automatic resource allocation device provided by an embodiment of the present invention, such as Figure 4 As shown, the device 200 includes:

[0091] Resource undertaker grading module 201, used to evaluate and grade resource undertakers;

[0092] An access resource scoring module 202, used to score current access resources;

[0093] The automatic resource allocation module 203 is used to automatically allocate the access resources to resource undertakers of corresponding levels according to the scores of the access resources.

[0094] Among them, the resource undertaker grading module 201 is also used to input the identity information and behavior data of the resource undertaker into the trained first scoring model, and output the score of the resource undertaker; set the scoring interval corresponding to each level of the resource undertaker; and set the corresponding level for the resource undertaker according to the score of the resource undertaker.

[0095] The access resource scoring module 202 is further configured to input the identity information and behavior data of the current user in the access resource into the trained second scoring model, and output the score of the user.

[0096] The automatic resource allocation module 203 is also used to input the user's score into a pre-trained allocation model to obtain the resource acceptance personnel level assigned to the user; wherein the pre-trained allocation model is obtained in the following manner: the historical user's score output by the scoring model is used as a sample, and the resource acceptance personnel level assigned to the historical user is used as a label, and the model is trained using a real-time allocation algorithm to obtain a trained allocation model; and resource acceptance personnel in an idle state are selected from the resource acceptance personnel level to serve the user. The automatic resource allocation module 203 is also used to set an initial average score for each level according to historical data, and set a user number threshold for each level; obtain the current user's score, and calculate the difference between the score and the average score of each level; and assign the current user to the level with the smallest difference. The automatic resource allocation module 203 is also used to detect in real time whether the number of users included in each level is lower than the user number threshold; if it is detected that the level includes a number of users lower than the user number threshold, the difference between the current user score and the average score of each level lower than the user number threshold is calculated respectively, and the current user is allocated to the level with the smallest difference among the levels lower than the threshold. After the current user is allocated to the level with the smallest difference, the automatic resource allocation module 203 is also used to calculate the average score of the user scores in each level; sort the levels in order from large to small according to the average scores of users of all levels; obtain the score of the next user, calculate the difference between the user score and the average score of each level after sorting, and allocate the user to the corresponding level according to the difference, until all users are allocated. The user number threshold is a preset value where the number of users in each level is not lower than the average value of the total number of users in all levels.

[0097] Figure 5 It is a structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device includes a processor and a memory. The memory is used to store a computer executable program. When the computer program is executed by the processor, the processor executes a method for automatically editing teaching videos.

[0098] like Figure 5 As shown, the electronic device is presented in the form of a general computing device. The processor may be one or more and work in coordination. The present invention does not exclude distributed processing, that is, the processor may be dispersed in different physical devices. The electronic device of the present invention is not limited to a single entity, but may also be the sum of multiple physical devices.

[0099] The memory stores a computer executable program, which is usually a machine-readable code. The computer-readable program can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least part of the steps in the method.

[0100] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0101] Optionally, in this embodiment, the electronic device further includes an I / O interface, which is used for the electronic device to exchange data with an external device. The I / O interface can represent one or more of several levels of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0102] It should be understood that Figure 5 The electronic device shown is only an example of the present invention, and the electronic device of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as display screens, and some electronic devices also include human-computer interaction elements such as buttons, keyboards, etc. As long as the electronic device can execute the computer-readable program in the memory to implement the method of the present invention or at least part of the steps of the method, it can be considered as an electronic device covered by the present invention.

[0103] Figure 6 Schematic diagram of a computer-readable recording medium provided by an embodiment of the present invention. Figure 6 As shown, a computer executable program is stored in a computer-readable recording medium, and when the computer executable program is executed, the above-mentioned teaching video automatic editing method of the present invention is realized. The computer-readable storage medium may include a data signal propagated in a baseband or as a part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, device, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0104] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium realizes the following functions: evaluating and grading resource undertakers; scoring current access resources; and automatically allocating the access resources to resource undertakers of corresponding levels based on the scores of the access resources.

[0105] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and the like, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0106] Through the above description of the implementation mode, it is easy for those skilled in the art to understand that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. contained in the system. The present invention can also be implemented by computer software that executes the method of the present invention. However, it should be noted that the computer software that executes the method of the present invention is not limited to being executed by one or a specific hardware entity, and it can also be implemented in a distributed manner by unspecified specific hardware, such as some method steps executed by the computer program can be executed on a mobile client, and another part can be executed in a smart meter, a smart recognition pen, etc. For computer software, the software product can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), or it can be distributed and stored on the network, as long as it enables the electronic device to execute the method according to the present invention.

[0107] In summary, the present invention can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that general data processing devices such as microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0108] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the present invention is not inherently related to any specific computer, virtual device or electronic device, and various general devices can also implement the present invention. The above description is only a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatic resource allocation, characterized in that: include: The first scoring model is trained by inputting the information and behavior data of resource undertakers, and the resource undertakers are evaluated and graded according to their different performance indicators; Score the current access resources, the higher the score, the better the quality of the current user accessing the resources; According to the access resource scores, the access resources are automatically and evenly allocated to the resource undertakers of the corresponding level in real time through the real-time allocation algorithm, so that the number of access resources allocated to the resource undertakers of each level is basically the same, including: Input the score of the access resource into a pre-trained allocation model to obtain the level of resource undertakers allocated to the access resource, including: setting an initial average score for each level according to historical data and setting a threshold for the number of users of the access resource for each level, obtaining the score of the current user of the current access resource, respectively calculating the difference between the score of the current user and the average score of each level, and allocating the current user to the level with the smallest difference; Next, the average score of the user scores in each level is calculated, the levels are sorted in descending order according to the average scores of the user scores of all levels, the score of the next user is obtained, the difference between the user score and the average score of each level after sorting is calculated respectively, and the user is assigned to the corresponding level according to the difference, until all users who access the resources are assigned, including: after sorting the levels, the number of levels that currently meet the requirements is determined, when there is only one level, the user is directly assigned to the level, when there are two levels, the user is assigned to the level closer to the average score, when there are more than two levels, the relationship between the maximum and minimum values ​​of the user score and the average score of each level is determined, if it is greater than the maximum value of the average score, the user is directly assigned to the level with the smallest sequence number, if it is less than the minimum value of the average score, the user is directly assigned to the level with the largest sequence number, if it is between the maximum average score and the minimum average score, the level with the maximum average score and the level with the minimum average score are excluded, and the steps of sorting all levels and determining the number of levels that meet the requirements are repeated until all users who access the resources are assigned; A resource undertaker who is idle is selected from the resource undertaker level to serve the access resource.

2. The automatic resource allocation method according to claim 1, characterized in that: The first scoring model is trained by inputting the information and behavior data of resource undertakers, and the resource undertakers are evaluated and graded according to their different performance indicators, including: Input the identity information and behavior data of the resource undertaker into the trained first scoring model, and output the score of the resource undertaker; According to the overall score, the scoring interval corresponding to each level of the resource undertaker is set so that the number of resource undertakers in each level is close; the number of levels and the scoring interval of each level are adjusted according to the resource undertaker; The resource undertaker is set to a level corresponding to the score range according to the score of the resource undertaker.

3. The automatic resource allocation method according to claim 1, characterized in that: The scoring of the current access resources includes: The identity information and behavior data of the current user in the access resource are input into the trained second scoring model, and the score of the current user in the access resource is output.

4. The automatic resource allocation method according to claim 1, characterized in that: The allocation model includes: training the machine learning model by running the real-time allocation algorithm through historical training samples or directly substituting the allocation algorithm into the ordinary model for use as the allocation model.

5. The automatic resource allocation method according to claim 1, characterized in that: Assigning the current user to the level with the smallest difference further includes: Real-time detection of whether the number of users in each level is lower than the threshold of the number of users at the corresponding level; If a level containing a number of users below the user number threshold is detected, the difference between the current user's score and the average score of each level below the user number threshold is calculated, and the current user is assigned to the level with the smallest difference among the levels below the threshold.

6. The automatic resource allocation method according to claim 1, characterized in that: The user number threshold is a preset value where the number of users at each level is not less than the average value of the total number of users at all levels.

7. A resource automatic allocation device, characterized in that: include: The resource undertaker grading module is used to evaluate and grade the resource undertakers according to their different performance indicators by inputting the trained first scoring model with the information and behavior data of the resource undertakers; The access resource scoring module is used to score the current access resources. The higher the score, the better the quality of the current user of the access resource. The automatic resource allocation module is used to automatically and evenly allocate access resources to resource undertakers of corresponding levels in real time according to the access resource scores through a real-time allocation algorithm, so that the number of access resources allocated to resource undertakers at each level is basically the same, including: Input the score of the access resource into a pre-trained allocation model to obtain the level of resource undertakers allocated to the access resource, including: setting an initial average score for each level according to historical data and setting a threshold of the number of users of the access resource for each level, obtaining the score of the current user of the current access resource, respectively calculating the difference between the score of the current user and the average score of each level, and allocating the current user to the level with the smallest difference; Next, the average score of the user scores in each level is calculated, the levels are sorted in descending order according to the average scores of the user scores of all levels, the score of the next user is obtained, the difference between the user score and the average score of each level after sorting is calculated respectively, and the user is assigned to the corresponding level according to the difference, until all users who access the resources are assigned, including: after sorting the levels, the number of levels that currently meet the requirements is determined, when there is only one level, the user is directly assigned to the level, when there are two levels, the user is assigned to the level closer to the average score, when there are more than two levels, the relationship between the maximum and minimum values ​​of the user score and the average score of each level is determined, if it is greater than the maximum value of the average score, the user is directly assigned to the level with the smallest sequence number, if it is less than the minimum value of the average score, the user is directly assigned to the level with the largest sequence number, if it is between the maximum average score and the minimum average score, the level with the maximum average score and the level with the minimum average score are excluded, and the steps of sorting all levels and determining the number of levels that meet the requirements are repeated until all users who access the resources are assigned; A resource undertaker who is idle is selected from the resource undertaker level to serve the access resource.

8. An electronic device, comprising a processor and a memory, wherein the memory is used to store a computer executable program, wherein: When the computer executable program is executed by the processor, the processor performs the method according to any one of claims 1 to 6.

Images