Method and device for determining target object and storage medium

Abstract

The invention relates to the technical field of service dispatching, in particular to a method and device for determining a target object and a storage medium. Comprising the following steps: acquiring a plurality of objects and at least one evaluation dimension of the plurality of objects for a current business demand of a user; determining an initial value of the interested object; determining the following probability of the interested object according to the initial value of the interested object and the first values of the plurality of objects; determining a first related object from other objects except the interested object according to the following probability; determining a final value of the interested object according to the first value of the first related object and the initial value; determining an updated numerical value of the interested object according to the final numerical value, and adding one to the number of iterations of the interested object; determining the offset degree of the interested object according to the final numerical value of the interested object obtained by the last iteration; and the object with the minimum offset degree in the multiple objects is determined as the target object, so that the business processing efficiency is improved, the user requirements are met, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the technical field of service dispatching, and in particular to a method, device and storage medium for determining a target object. Background Art

[0002] Work dispatch is an important part of the engineering service system. In a service system, there is often a scenario where a service order (work order) is assigned to an object (service engineer) to provide services to customers on-site or remotely. In the existing dispatch process, when selecting a service engineer, the system will query the objects with relevant service permissions under the department according to the department where the current operator is located. The operator selects in the object query list, and then the system will generate a corresponding dispatch order and send it to the interested object. After receiving the dispatch order, the interested object will provide services to the customer according to the instructions. The objects with relevant service permissions queried by the system are only searched from the database according to certain restrictions and displayed in the front-end list. There is no distinction between the objects available for dispatch in the list, and it is impossible to determine the best object for dispatch. This often results in the interested object being unable to solve the customer's problem and requiring repeated dispatches. On the one hand, it causes a waste of resources, and on the other hand, it causes the customer's problem to not be solved in a timely manner. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a method, device and storage medium for determining a target object, so as to solve the problem of resource waste and untimely service caused by the inability to accurately determine the best dispatch object in the prior art.

[0004] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for determining a target object, the method comprising:

[0005] Acquire multiple objects and at least one evaluation dimension of the multiple objects according to the current business needs of the user;

[0006] For any object of interest among the multiple objects, determining an initial value of the object of interest;

[0007] Determine a follow-up probability of the object of interest according to an initial value of the object of interest and first values ​​of the plurality of objects, wherein the first value is determined according to a historical maximum value and a historical minimum value of an evaluation dimension of each object;

[0008] determining a first related object from other objects other than the object of interest according to the follow-up probability;

[0009] determining a final value of the object of interest based on the first value and the initial value of the first related object;

[0010] Determine the updated value of the object of interest according to the final value, and increase the number of iterations of the object of interest by one;

[0011] Before the number of iterations reaches the preset number and the updated value reaches the preset upper limit, return to the step of determining the initial value of the object of interest until the number of iterations reaches the preset number;

[0012] Before the number of iterations reaches the preset number and the updated value does not reach the preset upper limit, return to the step of determining the following probability of the object of interest according to the initial value of the object of interest and the first values ​​of the plurality of objects until the number of iterations reaches the preset number;

[0013] determining a degree of displacement of the object of interest according to a final value of the object of interest obtained in the last iteration;

[0014] An object with the smallest deviation among the multiple objects is determined as a target object.

[0015] In an embodiment of the present application, determining the initial value of the object of interest includes: selecting any one object other than the object of interest as a second related object; determining the second value of an evaluation dimension of the object of interest based on the first value of the object of interest and the first value of the second related object; and determining the maximum value of the first value and the second value of the evaluation dimension of the object of interest as the initial value.

[0016] In an embodiment of the present application, determining the final value of the object of interest based on the first value and the initial value of the first related object includes: updating the second value of the object of interest based on the first value of the first related object; and determining the maximum value between the initial value and the updated second value of the object of interest as the final value of the object of interest.

[0017] In an embodiment of the present application, determining the initial numerical value of the object of interest includes: determining a first fitness of the object of interest based on a first numerical value of the object of interest and a weight factor of an evaluation dimension; determining a second fitness of the object of interest based on a second numerical value of the object of interest and the weight factor; when the first fitness of the object of interest is greater than the second fitness, determining the initial numerical value of the object of interest to be the first numerical value of the object of interest; when the first fitness of the object of interest is less than the second fitness, determining the initial numerical value of the object of interest to be the second numerical value of the object of interest.

[0018] In an embodiment of the present application, determining the follow probability of an object of interest based on an initial numerical value of the object of interest and first numerical values ​​of multiple objects includes: determining the first fitness of each object based on the first numerical value of each object and a weight factor; when the initial numerical value is the first numerical value of the object of interest, determining the follow probability as the ratio between the first fitness of the object of interest and the sum of the first fitnesses of the multiple objects; when the initial numerical value is the second numerical value of the object of interest, determining the follow probability as the ratio between the second fitness of the object of interest and the sum of the first fitnesses of the multiple objects.

[0019] In an embodiment of the present application, determining the updated value of the object of interest according to the final value includes: when the final value is the initial value, determining the updated value of the object of interest plus one; when the final value is not the initial value, returning the updated value to zero.

[0020] In the embodiment of the present application, determining the offset degree of the object of interest according to the final value of the object of interest obtained in the last iteration includes calculating the offset degree of the object of interest according to formula (1):

[0021]

[0022] Among them, f(x i ) is the offset degree of the object of interest i, x ij is the first value of the jth evaluation dimension of the object of interest i, v ij is the final value of the j-th evaluation dimension of the object of interest i obtained in the last iteration, and D is the total number of evaluation dimensions of the object of interest i.

[0023] In an embodiment of the present application, the method further includes: generating a work order for the target object according to current business needs and sending the work order to the target object, so that the target object provides services to the user based on the work order.

[0024] In an embodiment of the present application, the method also includes: arranging multiple objects in ascending order according to their offset degrees to obtain multiple sorted objects; obtaining an object selected by a user from the sorted multiple objects; generating a work order for the selected object according to current business needs and sending it to the selected object, so that the selected object can provide services to the user based on the work order.

[0025] In an embodiment of the present application, obtaining multiple objects and at least one evaluation dimension of the multiple objects for the user's current business needs includes: obtaining a query operation triggered by the user based on the current business needs; querying multiple objects from a database based on the query operation; obtaining a selection instruction for a candidate evaluation dimension in a rule resource pool triggered by the user based on the current business needs, wherein the rule resource pool includes multiple candidate evaluation dimensions; and reading corresponding candidate evaluation dimensions from the rule resource pool based on the selection instruction as evaluation dimensions for multiple objects.

[0026] A second aspect of the present application provides a device for determining a target object, including:

[0027] a memory configured to store instructions;

[0028] The processor is configured to call instructions from the memory and implement the above method for determining the target object when executing the instructions.

[0029] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the above-mentioned method for determining a target object.

[0030] Through the above technical scheme, the final value of the object of interest can be determined according to the initial value of the object of interest and the first value of the first related object, and the updated value corresponding to the object of interest can be determined according to the final value, and the number of iterations corresponding to the object of interest is increased by one; then, according to the number of iterations and the updated value, the different steps are returned to loop until the number of iterations reaches a preset number, and the degree of deviation of the object of interest is determined according to the final value of the object of interest obtained in the last iteration; finally, the object with the smallest degree of deviation among multiple objects is determined as the target object, so as to determine the target object that best meets the current business needs of the user, improve business processing efficiency, and solve user problems in a timely manner, meet user needs, and improve user experience.

[0031] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0033] Figure 1 A first flow chart of a method for determining a target object according to an embodiment of the present application is schematically shown;

[0034] Figure 2A schematic diagram of a rule resource pool according to an embodiment of the present application is schematically shown;

[0035] Figure 3 A second flow chart of a method for determining a target object according to an embodiment of the present application is schematically shown;

[0036] Figure 4 A third flow chart of a method for determining a target object according to an embodiment of the present application is schematically shown;

[0037] Figure 5 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0039] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0040] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0041] Figure 1 A first flow chart of a method for determining a target object according to an embodiment of the present application is schematically shown. Figure 1 As shown, an embodiment of the present application provides a method for determining a target object, which may include the following steps.

[0042] Step 101: Acquire multiple objects and at least one evaluation dimension of the multiple objects for the current business needs of the user.

[0043] The processor may obtain multiple objects and at least one evaluation dimension of the multiple objects for the current business needs of the user. The object may be a service engineer who solves the current business needs of the user, and the evaluation dimension may include busy and idle status, work order response rate, work order timely processing rate, evaluation score, and work location.

[0044] In an embodiment of the present application, obtaining multiple objects and at least one evaluation dimension of the multiple objects for the user's current business needs includes: obtaining a query operation triggered by the user based on the current business needs; querying multiple objects from a database based on the query operation; obtaining a selection instruction for a candidate evaluation dimension in a rule resource pool triggered by the user based on the current business needs, wherein the rule resource pool includes multiple candidate evaluation dimensions; and reading corresponding candidate evaluation dimensions from the rule resource pool based on the selection instruction as evaluation dimensions for multiple objects.

[0045] The processor can obtain multiple objects and at least one evaluation dimension of the multiple objects for the current business needs of the user. Specifically, the processor can obtain a query operation triggered by the user based on the current business needs. After obtaining the query operation, the processor can query multiple objects from the database based on the query operation. The processor can obtain a selection instruction for the selected evaluation dimensions in the rule resource pool triggered by the user based on the current business needs, wherein the rule resource pool includes multiple selected evaluation dimensions. After obtaining the selection instruction, the processor can read the corresponding selected evaluation dimensions from the rule resource pool based on the selection instruction as the evaluation dimensions of the multiple objects.

[0046] In one embodiment, Figure 2 As shown, the rule resource pool includes multiple rules to be selected (i.e., evaluation dimensions to be selected), such as busy / idle status, work order response rate, work saturation, timely work order processing rate, customer evaluation, and time to site. The processor can select rules from the rule resource pool based on the user's selection instructions, such as busy / idle status, work order response rate, work saturation, and time to site selected by the user. The processor can input the selected rules into the artificial bee colony algorithm engine to determine the degree of deviation of each service engineer.

[0047] Step 102: for any object of interest among the multiple objects, determine an initial value of the object of interest.

[0048] For any object of interest among the multiple objects, the processor may determine an initial value of the object of interest.

[0049] In an embodiment of the present application, determining the initial value of the object of interest includes: selecting any one object other than the object of interest as a second related object; determining the second value of an evaluation dimension of the object of interest based on the first value of the object of interest and the first value of the second related object; and determining the maximum value of the first value and the second value of the evaluation dimension of the object of interest as the initial value.

[0050] The processor may determine an initial value of the object of interest. Specifically, the processor may select any one of the objects other than the object of interest as the second related object. After obtaining the second related object, the processor may determine the second value of the evaluation dimension of the object of interest based on the first value of the object of interest and the first value of the second related object. After obtaining the second value of the object of interest, the processor may determine the maximum value of the first value and the second value of the evaluation dimension of the object of interest as the initial value. For example, for the jth evaluation dimension of the i-th object of interest, the processor may determine the maximum value of the evaluation dimension j based on the historical maximum value x of the evaluation dimension j. maxj and the historical minimum x minj Determine the first value x of the jth evaluation dimension of the i-th object of interest ij , that is, x ij =x minj +rand[0,1](x maxj -x minj ), where rand[0,1] is a function for generating a random number between 0 and 1. The processor may generate a random number x according to the first value x of the i-th object of interest. ij and the first value x of the jth evaluation dimension of the second related object k kj Determine the second value v of the jth evaluation dimension of the i-th object of interest ij , that is, v ij =x ij +rand[0,1](x ij -x kj ), where rand[0,1] is a function for generating a random number between 0 and 1. After obtaining the first value and the second value of the jth evaluation dimension of the ith object of interest, the processor may determine the maximum value of the first value and the second value of the jth evaluation dimension of the ith object of interest as the initial value.

[0051] In an embodiment of the present application, determining the initial numerical value of the object of interest includes: determining a first fitness of the object of interest based on a first numerical value of the object of interest and a weight factor of an evaluation dimension; determining a second fitness of the object of interest based on a second numerical value of the object of interest and the weight factor; when the first fitness of the object of interest is greater than the second fitness, determining the initial numerical value of the object of interest to be the first numerical value of the object of interest; when the first fitness of the object of interest is less than the second fitness, determining the initial numerical value of the object of interest to be the second numerical value of the object of interest.

[0052] The processor can determine the initial numerical value of the object of interest. Specifically, the processor can determine the first fitness of the object of interest based on the first numerical value of the object of interest and the weight factor of the evaluation dimension. And determine the second fitness of the object of interest based on the second numerical value of the object of interest and the weight factor. After obtaining the first fitness and the second fitness, the processor can determine whether the first fitness is greater than the second fitness. In the case where the first fitness of the object of interest is greater than the second fitness, the processor can determine that the initial numerical value of the object of interest is the first numerical value of the object of interest. In the case where the first fitness of the object of interest is less than the second fitness, the processor can determine that the initial numerical value of the object of interest is the second numerical value of the object of interest. For the i-th sensitive object, the processor can obtain the weight factor μ of the j-th evaluation dimension of the i-th sensitive object. j . And according to the weight factor μ of the jth evaluation dimension of the i-th sensitive object j and the first value x of the jth evaluation dimension of the i-th object of interest ij Determine the first fitness y1 of the object of interest i, that is Where D is the Dth evaluation dimension of the object of interest i. The processor can calculate the weight factor μ of the jth evaluation dimension of the i-th sensitive object according to the weight factor μ of the j-th evaluation dimension of the i-th sensitive object. j and the second value v of the jth evaluation dimension of the i-th object of interest ij Determine the second fitness y2 of the object of interest i, that is After obtaining the first fitness y1 and the second fitness y2 of the object of interest i, the processor may determine whether the first fitness y1 is greater than the second fitness y2. In the case of y1>y2, the processor may determine that the initial value of the object of interest is the first value x of the object of interest. ij In the case where y1<y2, the processor may determine the initial value of the object of interest to be the second value v of the object of interest. ij .

[0053] Step 103: determining the follow probability of the object of interest according to the initial value of the object of interest and the first values ​​of the plurality of objects, wherein the first value is determined according to the historical maximum value and the historical minimum value of the evaluation dimension of each object.

[0054] After obtaining the initial value of the object of interest, the processor may determine the follow probability of the object of interest according to the initial value of the object of interest and first values ​​of multiple objects, where the first value is determined according to the historical maximum and minimum values ​​of the evaluation dimension of each object.

[0055] In an embodiment of the present application, determining the follow probability of an object of interest based on an initial numerical value of the object of interest and first numerical values ​​of multiple objects includes: determining the first fitness of each object based on the first numerical value of each object and a weight factor; when the initial numerical value is the first numerical value of the object of interest, determining the follow probability as the ratio between the first fitness of the object of interest and the sum of the first fitnesses of the multiple objects; when the initial numerical value is the second numerical value of the object of interest, determining the follow probability as the ratio between the second fitness of the object of interest and the sum of the first fitnesses of the multiple objects.

[0056] The processor may determine the following probability of the object of interest according to the initial value of the object of interest and the first values ​​of the multiple objects. Specifically, the processor may determine the first fitness of each object according to the first value of each object and the weight factor. In the case where the initial value is the first value of the object of interest, the processor may determine the following probability as the ratio between the first fitness of the object of interest and the sum of the first fitness of the multiple objects, i.e., the following probability of the object of interest i Among them, y1 is the first fitness of the object of interest i, y1 n is the first fitness of the nth object, and M is the mth object. When the initial value is the second value of the object of interest, the processor can determine the ratio between the second fitness of the object of interest and the sum of the first fitness of multiple objects as the following probability, that is, the following probability of the object of interest i Among them, y2 is the second fitness of the object of interest i, y1 n is the first fitness of the nth object, and M is the mth object.

[0057] Step 104: determining a first related object from other objects other than the object of interest according to the follow-up probability.

[0058] Step 105: Determine a final value of the object of interest according to the first value of the first related object and the initial value.

[0059] After obtaining the follow-up probability of the object of interest, the processor may determine the first related object from other objects other than the object of interest according to the follow-up probability. For example, the processor may randomly sample from other objects based on the follow-up probability to obtain the first related object. After obtaining the first related object, the processor may determine the final value of the object of interest according to the first value and the initial value of the first related object.

[0060] In an embodiment of the present application, determining the final value of the object of interest based on the first value and the initial value of the first related object includes: updating the second value of the object of interest based on the first value of the first related object; and determining the maximum value between the initial value and the updated second value of the object of interest as the final value of the object of interest.

[0061] The processor may determine a final value of the object of interest based on the first value of the first related object and the initial value. Specifically, the processor may update the second value of the object of interest based on the first value of the first related object. After obtaining the updated second value of the object of interest, the processor may determine the maximum value of the initial value and the updated second value of the object of interest as the final value of the object of interest.

[0062] Step 106: Determine the updated value of the object of interest according to the final value, and increase the number of iterations of the object of interest by one.

[0063] After determining the final value of the object of interest, the processor may determine an updated value of the object of interest according to the final value, and increase the number of iterations of the object of interest by one.

[0064] In an embodiment of the present application, determining the updated value of the object of interest according to the final value includes: when the final value is the initial value, determining the updated value of the object of interest plus one; when the final value is not the initial value, returning the updated value to zero.

[0065] The processor may determine the updated value of the object of interest based on the final value. Specifically, the processor may determine whether the final value is the initial value. If the final value is the initial value, the processor may determine that the updated value of the object of interest is increased by one. If the final value is not the initial value, the processor may reset the updated value to zero.

[0066] Step 107: before the number of iterations reaches the preset number and the updated value reaches the preset upper limit, return to the step of determining the initial value of the object of interest until the number of iterations reaches the preset number.

[0067] Step 108: before the number of iterations reaches the preset number and the updated value does not reach the preset upper limit, return to the step of determining the follow probability of the object of interest based on the initial value of the object of interest and the first values ​​of multiple objects until the number of iterations reaches the preset number.

[0068] Step 109: Determine the degree of deviation of the object of interest according to the final value of the object of interest obtained in the last iteration.

[0069] Step 110: Determine the object with the smallest deviation among the multiple objects as the target object.

[0070] The processor can determine whether the number of iterations reaches a preset number of times, and determine whether the updated value reaches a preset upper limit value. The preset number of times can be determined based on actual conditions, and the preset upper limit value can be determined based on actual conditions. Before the number of iterations reaches the preset number of times and the updated value reaches the preset upper limit value, the processor can return to the step of determining the initial value of the object of interest until the number of iterations reaches the preset number of times. Before the number of iterations reaches the preset number of times and the updated value does not reach the preset upper limit value, the processor can return to the step of determining the follow-up probability of the object of interest based on the initial value of the object of interest and the first values ​​of multiple objects until the number of iterations reaches the preset number of times. After the number of iterations reaches the preset number of times, the processor can determine the degree of deviation of the object of interest based on the final value of the object of interest obtained in the last iteration. In an embodiment of the present application, determining the degree of deviation of the object of interest based on the final value of the object of interest obtained in the last iteration includes calculating the degree of deviation of the object of interest according to formula (1):

[0071]

[0072] Among them, f(x i ) is the offset degree of the object of interest i, x ij is the first value of the jth evaluation dimension of the object of interest i, v ij is the final value of the j-th evaluation dimension of the object of interest i obtained in the last iteration, and D is the total number of evaluation dimensions of the object of interest i.

[0073] After obtaining the degree of deviation of each object, the processor may determine the object with the smallest degree of deviation among the multiple objects as the target object.

[0074] In an embodiment of the present application, the method further includes: generating a work order for the target object according to current business needs and sending the work order to the target object, so that the target object provides services to the user based on the work order.

[0075] After determining the target object, the processor can generate a work order for the target object according to current business needs and send it to the target object, so that the target object can provide services to the user based on the work order to improve processing efficiency and better meet user needs.

[0076] In an embodiment of the present application, the method also includes: arranging multiple objects in ascending order according to their offset degrees to obtain multiple sorted objects; obtaining an object selected by a user from the sorted multiple objects; generating a work order for the selected object according to current business needs and sending it to the selected object, so that the selected object can provide services to the user based on the work order.

[0077] The processor may arrange the multiple objects in ascending order according to the offset degree of the multiple objects to obtain the sorted multiple objects. After obtaining the sorted multiple objects, the processor may obtain the object selected by the user from the sorted multiple objects. After obtaining the selected object, the processor may generate a work order for the selected object according to the current business needs and send it to the selected object, so that the selected object can provide services to the user based on the work order, thereby improving the user experience and speeding up the processing efficiency.

[0078] In the embodiments of the present application, Figure 3 As shown, the processor can obtain the current business needs of the user and select and assign people based on the current business needs. The processor can query the database (DB) for personnel based on some business rules. After querying the relevant personnel, the processor can obtain the user's setting rules, and process the queried personnel based on the rules and the artificial bee colony algorithm optimization engine to return qualified personnel. The qualified personnel are fed back to the user for the user to select personnel. A work order is generated based on the selected personnel, and the work order is sent to the service engineer (i.e., the selected personnel) so that the service engineer can perform the work assignment task. At the same time, the processor can record the data of the work order and the service engineer's service process to the DB (database).

[0079] Specifically, Figure 4As shown, in the artificial bee colony algorithm optimization engine, the honey source is equivalent to the object in the above embodiment. The processor can initialize the honey source to obtain the first value of the honey source. After the honey source is initialized, the processor can perform a field search based on the employment peak and greedily select a better honey source. Specifically, the processor can update the first value of the current honey source based on any one of the other honey sources in the field and the first value of the arbitrary honey source. The processor can determine the first fitness of the current honey source based on the first value of the current honey source, and determine the second fitness of the current honey source based on the updated first value. The processor can determine the initial value of the current honey source with a large fitness. The processor can select the employment peak by following the peak in a roulette manner, that is, the processor can calculate the follow probability, and select any one of the other honey sources based on the follow probability, and return to the step of updating the first value of the current honey source according to the first value of the arbitrary honey source to obtain a different updated first value. The processor can calculate whether the fitness value of the honey source selected by the follow peak is better than the original one. That is, it is judged whether the second fitness corresponding to the first value after each update is greater than the first fitness corresponding to the first value after the last update. When the fitness value of the nectar source selected by the follow peak is better than the original one, the processor can exploit the new nectar source and set its trial (i.e., the updated value above) to 0. When the fitness value of the nectar source selected by the follow peak is worse than the original one, the processor can continue to exploit the original nectar source and increase its trial by 1. The processor can determine whether the number of exploitations of the same nectar source has reached the maximum limit (preset upper limit value). When the maximum limit is reached, the processor can use the reconnaissance peak to globally search for new nectar sources and set its trial to 0. That is, the step of initializing the nectar source again and initializing a different first value for the current nectar source. When the limit is not reached, the processor can record the current first value of the current nectar source as the current optimal solution. The processor can determine whether the maximum number of iterations has been reached. When the maximum number of iterations has not been reached, the processor can return to the step of performing a field search based on the employment peak and greedily selecting a better nectar source until the maximum number of iterations is reached, and the program of the artificial bee colony algorithm optimization engine ends and outputs the optimal solution, that is, the optimal solution recorded when the maximum number of iterations is reached.

[0080] Through the above technical solution, it is possible to determine the target object that best meets the user's current business needs, improve business processing efficiency, and subsequently solve user problems in a timely manner, meet user needs, and improve user experience.

[0081] Figure 1 , Figure 3 as well as Figure 4 FIG. 1 is a flow chart of a method for determining a target object in one embodiment. Figure 1 , Figure 3 as well as Figure 4The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1 , Figure 3 as well as Figure 4 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0082] The present application also provides a device for determining a target object, including:

[0083] a memory configured to store instructions;

[0084] The processor is configured to call instructions from the memory and implement the above method for determining the target object when executing the instructions.

[0085] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for determining a target object.

[0086] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected by a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store initial values, first values, follow-up probabilities, final values, updated values, number of iterations and offset degree data. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for determining a target object is implemented.

[0087] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0088] The embodiment of the present application provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor executes the following steps when executing the program: obtaining multiple objects and at least one evaluation dimension of the multiple objects for the current business needs of a user; determining an initial value of the object of interest for any one of the multiple objects; determining a follow probability of the object of interest according to the initial value of the object of interest and the first values ​​of the multiple objects, wherein the first value is determined according to the historical maximum value and the historical minimum value of the evaluation dimension of each object; determining a first related object from other objects other than the object of interest according to the follow probability; determining a final value of the object of interest according to the first value of the first related object and the initial value; determining an updated value of the object of interest according to the final value, and adding one to the number of iterations of the object of interest; before the number of iterations reaches a preset number and the updated value reaches a preset upper limit, returning to the step of determining the initial value of the object of interest until the number of iterations reaches the preset number; before the number of iterations reaches the preset number and the updated value does not reach the preset upper limit, returning to the step of determining the follow probability of the object of interest according to the initial value of the object of interest and the first values ​​of the multiple objects until the number of iterations reaches the preset number; determining the degree of deviation of the object of interest according to the final value of the object of interest obtained in the last iteration; and determining the object with the smallest degree of deviation among the multiple objects as the target object.

[0089] In one embodiment, determining the initial value of the object of interest includes: selecting any one object other than the object of interest as a second related object; determining a second value of an evaluation dimension of the object of interest based on a first value of the object of interest and a first value of a second related object; and determining the maximum value of the first value and the second value of the evaluation dimension of the object of interest as the initial value.

[0090] In one embodiment, determining the final value of the object of interest based on the first value and the initial value of the first related object includes: updating the second value of the object of interest based on the first value of the first related object; and determining the maximum value between the initial value and the updated second value of the object of interest as the final value of the object of interest.

[0091] In one embodiment, determining the initial numerical value of the object of interest includes: determining a first fitness of the object of interest based on a first numerical value of the object of interest and a weight factor of an evaluation dimension; determining a second fitness of the object of interest based on a second numerical value of the object of interest and the weight factor; when the first fitness of the object of interest is greater than the second fitness, determining the initial numerical value of the object of interest to be the first numerical value of the object of interest; when the first fitness of the object of interest is less than the second fitness, determining the initial numerical value of the object of interest to be the second numerical value of the object of interest.

[0092] In one embodiment, determining the follow probability of an object of interest based on an initial numerical value of the object of interest and first numerical values ​​of multiple objects includes: determining the first fitness of each object based on the first numerical value of each object and a weight factor; when the initial numerical value is the first numerical value of the object of interest, determining the follow probability as the ratio between the first fitness of the object of interest and the sum of the first fitnesses of the multiple objects; when the initial numerical value is the second numerical value of the object of interest, determining the follow probability as the ratio between the second fitness of the object of interest and the sum of the first fitnesses of the multiple objects.

[0093] In one embodiment, determining the updated value of the object of interest according to the final value includes: if the final value is the initial value, determining the updated value of the object of interest plus one; if the final value is not the initial value, returning the updated value to zero.

[0094] In one embodiment, determining the offset degree of the object of interest according to the final value of the object of interest obtained in the last iteration includes calculating the offset degree of the object of interest according to formula (1):

[0095]

[0096] Among them, f(x i ) is the offset degree of the object of interest i, x ij is the first value of the jth evaluation dimension of the object of interest i, v ij is the final value of the j-th evaluation dimension of the object of interest i obtained in the last iteration, and D is the total number of evaluation dimensions of the object of interest i.

[0097] In one embodiment, the method further includes: generating a work order for the target object according to current business needs and sending the work order to the target object, so that the target object provides services to the user based on the work order.

[0098] In one embodiment, the method also includes: arranging the multiple objects in ascending order according to the degree of offset of the multiple objects to obtain the sorted multiple objects; obtaining the object selected by the user from the sorted multiple objects; generating a work order for the selected object according to current business needs and sending it to the selected object, so that the selected object can provide services to the user based on the work order.

[0099] In one embodiment, obtaining multiple objects and at least one evaluation dimension of the multiple objects for the user's current business needs includes: obtaining a query operation triggered by the user based on the current business needs; querying multiple objects from a database based on the query operation; obtaining a selection instruction for a candidate evaluation dimension in a rule resource pool triggered by the user based on the current business needs, wherein the rule resource pool includes multiple candidate evaluation dimensions; and reading corresponding candidate evaluation dimensions from the rule resource pool based on the selection instruction as evaluation dimensions for the multiple objects.

[0100] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initiates the method steps for determining a target object.

[0101] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0103] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0105] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0106] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0107] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0108] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0109] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining a target object, characterized in that: The method comprises: Acquire multiple objects for the current business needs of the user and at least one evaluation dimension of the multiple objects; For any object of interest among the multiple objects, determining an initial value of the object of interest; Determine a follow-up probability of the object of interest according to the initial value of the object of interest and the first values ​​of the multiple objects, wherein the first value is determined according to a historical maximum value and a historical minimum value of the evaluation dimension of each object; determining a first related object from other objects other than the object of interest according to the follow-up probability; determining a final value of the object of interest based on the first value of the first related object and the initial value; Determine an updated value of the object of interest according to the final value, and increase the number of iterations of the object of interest by one; Before the number of iterations reaches a preset number and the updated value reaches a preset upper limit, returning to the step of determining an initial value of the object of interest until the number of iterations reaches the preset number; Before the number of iterations reaches the preset number and the updated value does not reach the preset upper limit, return to the step of determining the following probability of the object of interest according to the initial value of the object of interest and the first values ​​of the multiple objects until the number of iterations reaches the preset number; Determining the degree of deviation of the object of interest according to a final value of the object of interest obtained in the last iteration; The object with the smallest deviation among the multiple objects is determined as the target object.

2. The method for determining a target object according to claim 1, characterized in that: Determining the initial value of the object of interest comprises: Any one of the objects other than the object of interest is selected as a second related object; Determine a second value of the evaluation dimension of the object of interest according to the first value of the object of interest and the first value of the second related object; The maximum value between the first value and the second value of the evaluation dimension of the object of interest is determined as the initial value.

3. The method for determining a target object according to claim 2, characterized in that: Determining the final value of the object of interest according to the first value of the first related object and the initial value comprises: updating a second value of the object of interest according to a first value of the first related object; A maximum value between the initial value and the updated second value of the object of interest is determined as a final value of the object of interest.

4. The method for determining a target object according to claim 2, characterized in that: Determining the initial value of the object of interest comprises: Determine a first fitness of the object of interest according to the first value of the object of interest and the weight factor of the evaluation dimension; determining a second fitness of the object of interest according to a second value of the object of interest and the weight factor; In a case where the first fitness of the object of interest is greater than the second fitness, determining the initial value of the object of interest to be the first value of the object of interest; In a case where the first fitness of the object of interest is less than the second fitness, the initial value of the object of interest is determined to be the second value of the object of interest.

5. The method for determining a target object according to claim 4, characterized in that: Determining the following probability of the object of interest according to the initial value of the object of interest and the first values ​​of the plurality of objects comprises: Determine a first fitness of each object according to the first value of each object and the weight factor; In a case where the initial value is the first value of the object of interest, determining a ratio between the first fitness of the object of interest and the sum of the first fitness of the plurality of objects as the following probability; In a case where the initial value is the second value of the object of interest, a ratio between the second fitness of the object of interest and the sum of the first fitness of the plurality of objects is determined as the follow probability.

6. The method for determining a target object according to claim 1, characterized in that: Determining the updated value of the object of interest according to the final value comprises: In a case where the final value is the initial value, determining an update value of the object of interest plus one; In the case where the final value is not the initial value, the updated value is reset to zero.

7. The method for determining a target object according to claim 1, characterized in that: Determining the offset degree of the object of interest according to the final value of the object of interest obtained in the last iteration includes calculating the offset degree of the object of interest according to formula (1): Among them, f(x i ) is the offset degree of the object of interest i, x ij is the first value of the jth evaluation dimension of the object of interest i, v ij is the final value of the j-th evaluation dimension of the object of interest i obtained in the last iteration, and D is the total number of evaluation dimensions of the object of interest i.

8. The method for determining a target object according to claim 1, characterized in that: The method further comprises: A work order for the target object is generated according to the current business demand and sent to the target object, so that the target object provides service to the user based on the work order.

9. The method for determining a target object according to claim 1, characterized in that: The method further comprises: Arrange the multiple objects in ascending order according to their offset degrees to obtain a plurality of sorted objects; Obtaining an object selected by the user from the sorted multiple objects; A work order for the selected object is generated according to the current business demand and sent to the selected object, so that the selected object provides service to the user based on the work order.

10. The method for determining a target object according to claim 1, characterized in that: The acquiring of multiple objects for the current business needs of the user and at least one evaluation dimension of the multiple objects includes: Acquire the query operation triggered by the user based on the current business demand; querying the plurality of objects from a database based on the query operation; Acquire a selection instruction for a candidate evaluation dimension in a rule resource pool triggered by the user based on the current business demand, wherein the rule resource pool includes a plurality of candidate evaluation dimensions; Based on the selection instruction, corresponding to-be-selected evaluation dimensions are read from the rule resource pool to serve as evaluation dimensions for the multiple objects.

11. A device for determining a target object, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the method for determining a target object according to any one of claims 1 to 10 when executing the instructions.

12. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions, which are used to enable a machine to execute the method for determining a target object according to any one of claims 1 to 10.

Images