Data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a storage medium, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining corresponding delivery order information, delivery vehicle information and delivery station information in response to a processing instruction of article delivery, so as to generate an initial scheme; inputting the initial scheme into a preset calculation model to obtain a corresponding output result, and calculating an evaluation value corresponding to the output result; calculating the adoption confidence coefficient of the output result to update an output result set in combination with the evaluation value, and selecting a new initial scheme from the output result set to input the new initial scheme into the calculation model and obtain an output result again; and in response to triggering of an ending instruction, screening an output result meeting a preset condition from the result set to determine a distribution scheme for article distribution. According to the embodiment, the problems that the distribution scheme cannot be adopted and needs to be manually adjusted, and the article distribution efficiency is reduced can be solved.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a data processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the logistics and transportation sector, multi-point delivery is a common scenario. In such cases, due to the large number of delivery points, it's difficult to directly determine the optimal route planning and transportation costs, making the selection of a reasonable delivery plan crucial. Related technologies typically use cost or delivery distance as the optimal objective, employing heuristic algorithms to build models that output delivery plans. However, these plans often only consider cost or delivery distance, making them susceptible to problems such as uneven vehicle allocation leading to uneven workloads for delivery personnel. This can result in unacceptable delivery plans requiring manual adjustments and reduced delivery efficiency. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a data processing method, apparatus, electronic device, and storage medium that can solve the problem that delivery plans cannot be adopted and require manual adjustments, thus reducing the efficiency of goods delivery.

[0004] To achieve the above objectives, according to one aspect of the present invention, a data processing method is provided.

[0005] An embodiment of the present invention provides a data processing method comprising: in response to a processing instruction for item delivery, acquiring corresponding delivery order information, delivery vehicle information, and delivery station information to generate an initial plan; inputting the initial plan into a preset calculation model to obtain a corresponding output result; calling a preset evaluation model to calculate an evaluation value corresponding to the output result; calling a preset adoption model to calculate the adoption confidence of the output result, updating the output result set in conjunction with the evaluation value, and selecting a new initial plan from the output result set to input into the calculation model and obtain an output result again; wherein the adoption model is pre-trained based on adoption information of historical delivery plans; in response to an end instruction being triggered, filtering output results that meet preset conditions from the result set to determine the delivery plan for the item delivery.

[0006] In one embodiment, invoking a preset adoption model to calculate the adoption confidence of the output result, and updating the output result set in conjunction with the evaluation value, includes: invoking a preset adoption model to calculate the adoption confidence of the output result, and calculating the total score of the output result based on the evaluation value and the adoption confidence; adding the output result to the output result set in response to the total score satisfying a first condition; and discarding the output result in response to the total score not satisfying the first condition.

[0007] In another embodiment, calculating the total score of the output result based on the evaluation value and the adoption confidence level includes: determining a first score of the output result based on the evaluation value; determining the corresponding adoption coefficient based on the interval level to which the adoption confidence level belongs; calculating a second score based on the adoption coefficient and the adoption confidence level; and superimposing the first score and the second score to obtain the total score of the output result.

[0008] In another embodiment, selecting a new initial solution from the set of output results includes: based on the pending output results in the set of output results whose evaluation values ​​belong to a preset range, determining the pending output result with the highest adoption confidence as the new initial solution.

[0009] In another embodiment, a preset adoption model is invoked to calculate the adoption confidence of the output result, so as to update the output result set in conjunction with the evaluation value, and a new initial solution is selected from the output result set, including: adding the output result to the output result set in response to the evaluation value satisfying a second condition; discarding the output result in response to the evaluation value not satisfying the second condition; invoking the preset adoption model to calculate the adoption confidence of the output result, calculating the total score of the output result based on the evaluation value and the adoption confidence; and selecting a new initial solution from the output result set based on the total score.

[0010] In another embodiment, the method further includes: acquiring multiple historical delivery plans to extract feature data corresponding to preset features for each historical delivery plan; adding adoption tags to each historical delivery plan with corresponding feature data to execute the training program of the adoption model based on the feature data after adding the adoption tags.

[0011] To achieve the above objectives, according to another aspect of the present invention, a data processing apparatus is provided.

[0012] An embodiment of the present invention provides a data processing apparatus comprising: an acquisition unit, configured to acquire corresponding delivery order information, delivery vehicle information, and delivery station information in response to a processing instruction for item delivery, to generate an initial plan; a calculation unit, configured to input the initial plan into a preset calculation model to obtain a corresponding output result, and call a preset evaluation model to calculate an evaluation value corresponding to the output result; an update unit, configured to call a preset adoption model to calculate the adoption confidence of the output result, to update the output result set in conjunction with the evaluation value, and to select a new initial plan from the output result set to input into the calculation model and obtain an output result again; wherein the adoption model is pre-trained based on adoption information of historical delivery plans; and a determination unit, configured to filter output results that meet preset conditions from the result set in response to an end instruction being triggered, to determine the delivery plan for the item delivery.

[0013] In one embodiment, the update unit is specifically configured to: invoke a preset adoption model to calculate the adoption confidence of the output result, so as to calculate the total score of the output result based on the evaluation value and the adoption confidence; in response to the total score satisfying a first condition, add the output result to the output result set; in response to the total score not satisfying the first condition, discard the output result.

[0014] In another embodiment, the updating unit is specifically configured to: determine a first score for the output result based on the evaluation value; determine the corresponding adoption coefficient based on the interval level to which the adoption confidence level belongs; calculate a second score based on the adoption coefficient and the adoption confidence level; and superimpose the first score and the second score to obtain the total score of the output result.

[0015] In another embodiment, the updating unit is specifically used to: determine the pending output result with the highest adoption confidence as the new initial solution based on the pending output results in the set of output results whose evaluation values ​​belong to a preset range.

[0016] In another embodiment, the updating unit is specifically configured to: add the output result to the output result set in response to the evaluation value satisfying the second condition; discard the output result in response to the evaluation value not satisfying the second condition; call a preset adoption model to calculate the adoption confidence of the output result, calculate the total score of the output result based on the evaluation value and the adoption confidence; and select a new initial solution from the output result set based on the total score.

[0017] In another embodiment, the apparatus further includes: an extraction unit for acquiring multiple historical delivery plans to extract feature data corresponding to preset features of each historical delivery plan; and a training unit for adding adoption tags to each historical delivery plan with corresponding feature data to execute the training program of the adoption model based on the feature data after adding the adoption tags.

[0018] To achieve the above objectives, according to another aspect of the present invention, an electronic device is provided.

[0019] An electronic device according to an embodiment of the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided in the embodiment of the present invention.

[0020] To achieve the above objectives, according to another aspect of the present invention, a computer-readable medium is provided.

[0021] An embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the data processing method provided in the embodiment of the present invention.

[0022] To achieve the above objectives, according to another aspect of the present invention, a computer program product is provided.

[0023] A computer program product according to an embodiment of the present invention includes a computer program that, when executed by a processor, implements the data processing method provided in the embodiment of the present invention.

[0024] One embodiment of the above invention has the following advantages or beneficial effects: In this embodiment, in response to the processing instruction for item delivery, the corresponding delivery task information, delivery vehicle information, and delivery station information can be obtained first to generate an initial plan, i.e., an initial item delivery plan. Then, the initial plan is input into a preset calculation model to obtain the corresponding output result. Next, a preset evaluation model is called to calculate the evaluation value corresponding to the output result, and a preset adoption model is called to calculate the adoption confidence of the output result. The output result set is updated in conjunction with the evaluation value, and a new initial plan is selected from the output result set to be input into the calculation model and the output result is obtained again. This iterative operation can repeatedly yield the output result, i.e., multiple delivery plans are obtained. When the termination instruction is triggered, the iteration operation ends, and the output result that meets the preset conditions is selected from the result set to determine the item delivery plan. Since the adoption model is pre-trained based on the adoption information of historical delivery plans, the evaluation of the output result or the selection of a new initial plan incorporates the factor of whether the delivery plan has been adopted. This increases the probability of adoption of the confirmed delivery plan while meeting the optimization objective, making the confirmed delivery plan better meet actual delivery needs and improve delivery efficiency.

[0025] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0026] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein: Figure 1 This is a schematic diagram of a main flow of a data processing method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of a main process for determining the adoption model according to an embodiment of the present invention; Figure 3 This is a schematic diagram of another main flow of a data processing method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the main units of a data processing apparatus according to an embodiment of the present invention; Figure 5 This is an exemplary system architecture diagram in which embodiments of the present invention can be applied; Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing embodiments of the present invention. Detailed Implementation

[0027] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0028] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0029] This invention provides a data processing system for determining delivery plans for goods. Taking a multi-location delivery scenario as an example, this invention involves delivering multiple orders to various locations via vehicles. In related technologies, delivery plans that meet optimization objectives can typically be generated using a pre-set calculation model. However, these models often suffer from uneven workload distribution among delivery personnel and uneven order allocation among vehicles, making them difficult to implement offline or resulting in a poor user experience. Consequently, they are frequently rejected or require manual adjustments, leading to a low adoption rate and low order delivery efficiency. This invention incorporates delivery plan adoption information into the calculation model, adding adoption factors during the plan generation process. This makes the generated delivery plans more likely to be adopted while meeting optimization objectives. In other words, the delivery plans not only meet optimization requirements but also integrate multiple influencing factors, making them more suitable for offline execution and improving both adoption rate and order delivery efficiency.

[0030] It should be noted that, in this embodiment of the invention, the computational model is implemented using the ALNS (Adaptive Large Neighborhood Search, a heuristic algorithm) algorithm as an example, and an adoption factor is incorporated into its computation process.

[0031] This invention provides a data processing method, which can be executed by a data processing system, such as... Figure 1 As shown, the method includes the following steps.

[0032] S101: In response to the processing instruction for item delivery, obtain the corresponding delivery order information, delivery vehicle information and delivery station information to generate an initial plan.

[0033] The item delivery processing instruction specifies the delivery plan, which may include order information such as order identifiers. Order delivery requires delivery vehicles, and delivery stations indicate the destinations for the orders, typically determined by the order's recipient information. Therefore, this step, in response to the item delivery processing instruction, retrieves the corresponding delivery order information, delivery vehicle information, and delivery station information. The delivery plan specifies the required delivery vehicles and the delivery orders to be executed by each vehicle.

[0034] In this step, an initial scheme can be generated first, given the initial state. The generation method is not limited. Specifically, the initial scheme can be constructed according to certain rules; for example, a saving algorithm or a clustering algorithm can be used.

[0035] S102: Input the initial scheme into the preset calculation model, obtain the corresponding output result, call the preset evaluation model to calculate the evaluation value corresponding to the output result.

[0036] The computational model can be pre-trained, taking the ALNS algorithm as an example. After inputting the initial solution into the pre-set computational model, the model can select the ruin and insert operators to be used in this iteration based on the weights of each operator. Multiple ruin and insert operators can be added based on specific business attributes. For example, in this embodiment, the ruin operator can include: random deletion, deletion of the worst, deletion of the closest, linear (same vehicle) deletion, cluster-based deletion, deletion of the largest vehicle type, etc.; the insert operator can include: optimal insertion, distance-based insertion, etc. Specifically, the operator selection method can be a weight-based roulette wheel selection. After selecting the operators, the initial solution can be ruined based on the selected ruin operator, deleting some nodes to form an infeasible solution; then, the deleted nodes can be re-inserted into the infeasible solution based on the selected insert operator, forming a new feasible solution, thus obtaining the corresponding output result.

[0037] An evaluation model is set up within the computational model to assess and score the output results based on the corresponding optimization objectives, i.e., the evaluation value corresponding to the output results. The optimization objectives can be set based on requirements, such as shortest distance, shortest time, optimal cost, fewest vehicles, balanced locations, and balanced time. The evaluation model can be implemented based on the calculation method of the optimization objectives.

[0038] S103: Call the preset adoption model, calculate the adoption confidence of the output results, update the output result set in combination with the evaluation value, and select a new initial scheme from the output result set to input into the calculation model and obtain the output results again.

[0039] The adoption model is pre-trained based on adoption information from historical delivery plans. In this embodiment of the invention, the adoption model incorporates adoption factors into the calculation of the delivery plan. Inputting the output result into the adoption model allows for the calculation of the adoption confidence score, representing the score at which the output result is adopted. Thus, in this embodiment of the invention, the evaluation model scores the output result based on the optimization objective and the adoption confidence score based on the adoption model, thereby enabling the operation of whether to accept the output result and selecting a new initial result for the next round of calculation.

[0040] In the ALNS algorithm, an output result set is established, which can be stored in a list. After each output result is obtained, it is determined whether to accept it. If accepted, it is added to the output result set; otherwise, it is discarded, thus updating the output result set. Furthermore, in order to perform the next round of calculation, an output result needs to be selected from the output result set as the new initial result for the next round of calculation.

[0041] Specifically, on the one hand, updating the output result set in this step can be performed as follows: calling the preset adoption model, calculating the adoption confidence of the output result, and calculating the total score of the output result based on the evaluation value and the adoption confidence; in response to the total score meeting the first condition, adding the output result to the output result set; in response to the total score not meeting the first condition, discarding the output result.

[0042] This step combines the evaluation value and the adoption confidence level to determine whether to accept the output result; that is, the total score of the output result is calculated based on the evaluation value and the adoption confidence level. The acceptance strategy can be preset, such as a greedy strategy, a threshold strategy, or a simulated annealing strategy. The acceptance strategy then determines the first condition to decide whether to add the output result to the output result set. For example, the first condition could be that the total score is greater than a preset threshold.

[0043] The overall score can be calculated as follows: First, determine the first score based on the evaluation value; second, determine the corresponding adoption coefficient based on the adoption confidence level interval; third, calculate the second score based on the adoption coefficient and adoption confidence level; finally, sum the first and second scores to obtain the overall score. In this step, the adoption confidence level can be divided into intervals, with different adoption coefficients set for different intervals. This allows the determination of the adoption coefficient corresponding to the output result, which is then multiplied by the adoption confidence level and adoption coefficient to determine the second score. The summation of the first and second scores can be achieved through methods such as summation, pre-weighted summation, etc.

[0044] It should be noted that after updating the output result set with the total score in this step, a new initial solution can be determined from the output result set based on the evaluation value and adoption confidence level. Specifically, this can be executed as follows: based on the pending output results in the output result set whose evaluation values ​​fall within a preset range, the pending output result with the highest adoption confidence level is determined as the new initial solution. The preset range can be set based on requirements.

[0045] Specifically, on the other hand, updating the output result set and determining the new initial solution in this step can be performed as follows: in response to the evaluation value meeting the second condition, add the output result to the output result set; in response to the evaluation value not meeting the second condition, discard the output result; call the preset adoption model, calculate the adoption confidence of the output result, calculate the total score of the output result based on the evaluation value and the adoption confidence; select a new initial solution from the output result set based on the total score.

[0046] In this step, the decision to add the output result to the output result set is based on the score. The second condition can be set to be greater than a preset evaluation threshold. After updating the output result set, the adoption confidence of the output result is calculated, and then the total score is calculated. A new initial solution is then selected from the output result set based on the total score.

[0047] In this embodiment of the invention, after a new initial scheme is determined, it is input into the calculation model so that a new output result can be calculated again. Then, the output result set is updated again and a new initial scheme for the next round is selected based on the above principle. This process is repeated in a loop to obtain an output result set that includes more output results.

[0048] It should be noted that, in this embodiment of the invention, when a new initial solution is input into the computation model each time, the weights of the `ruin` and `insert` operators can be updated based on the quality of the previous output result. For example, the quality of the output result can include: better than the optimal solution, better than the output result of the previous round, worse than the output result of the previous round, etc., thereby updating the weights of the operators. Generally, the better the quality of the output result, the more the weights of the `ruin` and `insert` operators used to calculate the output result are increased, thus making it easier for operators that can produce better output results to be selected.

[0049] S104: In response to the termination command being triggered, filter the output results that meet the preset conditions from the result set to determine the delivery plan for the item delivery.

[0050] The "End Command" indicates the instruction to terminate the calculation of the output results. Conditions for triggering the end command can usually be preset, such as reaching a certain number of iterations or a specified time for the calculation model. Once the end command is triggered, the calculation of the output results ends, allowing the selection of output results that meet the preset conditions from the result set to determine the appropriate delivery plan for the item. The preset condition can typically be set as the optimal output result, specifically the output result with the highest evaluation value. If output results with the same evaluation value exist, they can be selected based on the acceptance confidence level.

[0051] Once the delivery plan is determined in this step, it can be sent to the corresponding delivery system so that the order can be delivered based on the delivery plan.

[0052] It should be noted that by incorporating an adoption prediction model into the calculation process, outputs with high adoption rates are more likely to be accepted and added to the output set, or outputs with high adoption rates are more likely to be selected as the new initial solution for the next iteration, thereby guiding the direction of finding delivery solutions and making it easier to output delivery solutions with higher adoption rates.

[0053] In this embodiment of the invention, since the adoption model is pre-trained based on the adoption information of historical delivery plans, the evaluation of the output results or the selection of a new initial plan both incorporate the factor of whether the delivery plan has been adopted. This increases the probability of the confirmed delivery plan being adopted under the premise that it meets the optimization objective, so that the confirmed delivery plan can better meet the actual delivery needs and improve delivery efficiency.

[0054] This invention provides a method for determining an adoption model, which can be executed by a data processing system, such as... Figure 2 As shown, the method includes the following steps.

[0055] S201: Obtain multiple historical delivery plans to extract feature data corresponding to preset features of each historical delivery plan.

[0056] Historical delivery plans can be obtained based on historical records, which may include the specific implementation details of the delivery. Pre-configured features are set in advance; in this embodiment, features as shown in Table 1 can be set, and the influence weight of each feature on the delivery plan can be evaluated. Then, features used to train the adoption model can be selected based on these weights.

[0057] In this step, the extracted feature data can be cleaned, such as removing some empty data, and then encoded for use in model training.

[0058] S202: Add adoption tags to each historical delivery plan with corresponding feature data, and execute the training program of the adoption model based on the feature data after adding adoption tags.

[0059] The adoption tag can be set based on requirements, such as a vehicle model adoption tag or a solution full adoption tag.

[0060] The vehicle model adoption label can be added in the following ways: If all orders in a delivery plan do not have their vehicle models manually adjusted, the vehicle model is labeled as adopted; otherwise, it is labeled as not adopted. Alternatively, if any order in a delivery plan does not have its vehicle model manually adjusted, the vehicle model is labeled as adopted; otherwise, it is labeled as not adopted. Or, if the number of orders with a corresponding vehicle model that has not been manually adjusted is higher than the number of orders with a corresponding vehicle model that has been manually adjusted, the vehicle model is labeled as adopted; otherwise, it is labeled as not adopted.

[0061] The label "fully adopted" can be added as follows: if all deliveries in all orders included in a delivery plan have not been modified (orders have not been added or deleted) and the corresponding vehicle models have not been adjusted, then the label is "fully adopted"; otherwise, the label is "not fully adopted".

[0062] It should be noted that the adopted model in the embodiments of the present invention can be a machine learning model, such as a random forest algorithm, and the training program can be a training program for a machine learning model.

[0063] In this embodiment of the invention, the adoption model is trained using historical delivery plans to obtain an adoption model for determining delivery plans. This increases the probability of the confirmed delivery plan being adopted while meeting the optimization objective, thereby making the confirmed delivery plan better meet actual delivery needs and improve delivery efficiency.

[0064] The following is combined Figure 3 The illustrated embodiments provide a detailed description of the data processing methods in the embodiments of the present invention, such as... Figure 3 As shown, the method includes the following steps.

[0065] S301: In response to the processing instruction for item delivery, obtain the corresponding delivery order information, delivery vehicle information and delivery station information to generate an initial plan.

[0066] S302: Input the initial scheme into the preset calculation model, obtain the corresponding output result, call the preset evaluation model to calculate the evaluation value corresponding to the output result.

[0067] S303: Call the preset adoption model, calculate the adoption confidence of the output results, and calculate the total score of the output results based on the evaluation value and the adoption confidence.

[0068] S304: In response to the total score meeting the first condition, add the output result to the output result set; in response to the total score not meeting the first condition, discard the output result.

[0069] S305: Based on the pending output results whose evaluation values ​​in the output result set belong to a preset interval, the pending output result with the highest adoption confidence is determined as the new initial solution.

[0070] S306: Increment the iteration count by 1, and determine whether the iteration count is greater than the iteration count threshold. If yes, proceed to step S307; otherwise, proceed to step S302.

[0071] S307: Filter the output results that meet the preset conditions from the output result set to determine the delivery plan for the item delivery.

[0072] It should be noted that the data processing principle in the embodiments of the present invention is the same as... Figure 1 The data processing principles in the illustrated embodiments are the same and will not be repeated here.

[0073] To address the problems existing in the prior art, embodiments of the present invention provide a data processing apparatus 400, such as... Figure 4 As shown, the device 400 includes: an acquisition unit 401, configured to acquire corresponding delivery order information, delivery vehicle information, and delivery station information in response to a processing instruction for item delivery, to generate an initial plan; a calculation unit 402, configured to input the initial plan into a preset calculation model to obtain a corresponding output result, and call a preset evaluation model to calculate an evaluation value corresponding to the output result; an update unit 402, configured to call a preset adoption model to calculate the adoption confidence of the output result, to update the output result set in combination with the evaluation value, and to select a new initial plan from the output result set to input into the calculation model and obtain an output result again; wherein, the adoption model is pre-trained based on the adoption information of historical delivery plans; and a determination unit 404, configured to filter output results that meet preset conditions from the result set in response to an end instruction being triggered, to determine the delivery plan for the item delivery.

[0074] It should be understood that the manner in which embodiments of the present invention are implemented is different from the implementation method. Figure 1 The embodiments shown are the same and will not be described again here.

[0075] In one embodiment, the update unit 403 is specifically configured to: invoke a preset adoption model, calculate the adoption confidence of the output result, and calculate the total score of the output result based on the evaluation value and the adoption confidence; in response to the total score satisfying a first condition, add the output result to the output result set; and in response to the total score not satisfying the first condition, discard the output result.

[0076] In another embodiment, the update unit 403 is specifically configured to: determine a first score of the output result based on the evaluation value; determine the corresponding adoption coefficient based on the interval level to which the adoption confidence level belongs; calculate a second score based on the adoption coefficient and the adoption confidence level; and superimpose the first score and the second score to obtain the total score of the output result.

[0077] In another embodiment, the updating unit 403 is specifically used to: based on the pending output results in the set of output results whose evaluation values ​​belong to a preset range, determine the pending output result with the highest adoption confidence as the new initial solution.

[0078] In another embodiment, the update unit 403 is specifically configured to: add the output result to the output result set in response to the evaluation value satisfying the second condition; discard the output result in response to the evaluation value not satisfying the second condition; call a preset adoption model to calculate the adoption confidence of the output result, calculate the total score of the output result based on the evaluation value and the adoption confidence; and select a new initial solution from the output result set based on the total score.

[0079] In another embodiment, the device 400 further includes: an extraction unit for acquiring multiple historical delivery plans to extract feature data corresponding to preset features of each historical delivery plan; and a training unit for adding adoption tags to each historical delivery plan with corresponding feature data to execute the training program of the adoption model based on the feature data after adding the adoption tags.

[0080] It should be understood that the manner in which embodiments of the present invention are implemented is different from the implementation method. Figure 1 , 2 The same method is used in the embodiments shown in 1 and 3, and will not be described again here.

[0081] In this embodiment of the invention, since the adoption model is pre-trained based on the adoption information of historical delivery plans, the evaluation of the output results or the selection of a new initial plan both incorporate the factor of whether the delivery plan has been adopted. This increases the probability of the confirmed delivery plan being adopted under the premise that it meets the optimization objective, so that the confirmed delivery plan can better meet the actual delivery needs and improve delivery efficiency.

[0082] According to embodiments of the present invention, an electronic device and a readable storage medium are also provided.

[0083] An electronic device according to an embodiment of the present invention includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the data processing method provided in the embodiment of the present invention.

[0084] Figure 5 An exemplary system architecture 500 is shown, in which a data processing method or data processing apparatus to which embodiments of the present invention can be applied is illustrated.

[0085] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, and 503, a network 504, and a server 505. Network 504 serves as the medium for providing communication links between terminal devices 501, 502, and 503 and server 505. Network 504 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0086] Users can use terminal devices 501, 502, and 503 to interact with server 505 via network 504 to receive or send messages, etc. Various client applications can be installed on terminal devices 501, 502, and 503.

[0087] Terminal devices 501, 502, and 503 can be, but are not limited to, smartphones, tablets, laptops, and desktop computers, etc.

[0088] Server 505 can be a server that provides various services. The server can analyze and process data such as received product information query requests, and feed back the processing results (such as product information - just an example) to the terminal device.

[0089] It should be noted that the data processing method provided in the embodiments of the present invention is generally executed by server 505, and correspondingly, the data processing device is generally located in server 505.

[0090] It should be understood that Figure 5 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0091] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing embodiments of the present invention. Figure 6The computer system shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0092] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0093] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0094] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this invention.

[0095] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a unit, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The units described in the embodiments of the present invention can be implemented in software or hardware. The described units can also be housed in a processor; for example, a processor can be described as including an acquisition unit, a calculation unit, an update unit, and a determination unit. The names of these units do not necessarily limit the specific unit; for example, an acquisition unit can also be described as a "unit that acquires functions."

[0098] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs that, when executed by the device, cause the device to perform the data processing method provided by the present invention.

[0099] In another aspect, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the data processing method provided in the embodiments of the present invention.

[0100] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data processing method, characterized in that, include: In response to the processing instructions for item delivery, obtain the corresponding delivery order information, delivery vehicle information, and delivery station information to generate an initial plan; The initial scheme is input into a preset calculation model to obtain the corresponding output result. The preset evaluation model is then called to calculate the evaluation value corresponding to the output result. A preset adoption model is invoked to calculate the adoption confidence of the output results, and the output result set is updated in combination with the evaluation value. A new initial scheme is selected from the output result set to be input into the calculation model and the output results are obtained again. The adoption model is pre-trained based on the adoption information of historical delivery schemes. In response to the termination command being triggered, output results that meet preset conditions are filtered from the result set to determine the delivery plan for the item.

2. The method according to claim 1, characterized in that, Invoke a preset adoption model to calculate the adoption confidence score of the output results, and update the output result set in conjunction with the evaluation value, including: A preset adoption model is invoked to calculate the adoption confidence score of the output result, and the total score of the output result is calculated based on the evaluation value and the adoption confidence score. If the total score satisfies the first condition, the output result is added to the output result set; if the total score does not satisfy the first condition, the output result is discarded.

3. The method according to claim 2, characterized in that, The total score of the output result is calculated based on the evaluation value and the adoption confidence level, including: A first score for the output result is determined based on the evaluation value; Based on the interval level to which the adoption confidence level belongs, the corresponding adoption coefficient is determined, and the second score is calculated based on the adoption coefficient and the adoption confidence level; The first score and the second score are added together to obtain the total score of the output result.

4. The method according to claim 2, characterized in that, Selecting a new initial scheme from the set of output results includes: Based on the pending output results whose evaluation values ​​belong to a preset range in the set of output results, the pending output result with the highest adoption confidence is determined as the new initial solution.

5. The method according to claim 1, characterized in that, Invoke a preset adoption model, calculate the adoption confidence of the output results, update the output result set in conjunction with the evaluation value, and select a new initial solution from the output result set, including: In response to the evaluation value satisfying the second condition, the output result is added to the output result set; in response to the evaluation value not satisfying the second condition, the output result is discarded. A preset adoption model is invoked to calculate the adoption confidence score of the output result, and the total score of the output result is calculated based on the evaluation value and the adoption confidence score. A new initial scheme is selected from the set of output results based on the total score.

6. The method according to claim 1, characterized in that, Also includes: Multiple historical delivery plans are obtained to extract feature data corresponding to preset features of each historical delivery plan; The adoption tags corresponding to the historical delivery schemes are added to the feature data, and the training program of the adoption model is executed based on the feature data after adding the adoption tags.

7. A data processing apparatus, characterized in that, include: The acquisition unit is used to respond to the processing instructions for item delivery by acquiring the corresponding delivery order information, delivery vehicle information, and delivery station information to generate an initial plan; The calculation unit is used to input the initial scheme into a preset calculation model, obtain the corresponding output result, and call a preset evaluation model to calculate the evaluation value corresponding to the output result. An update unit is used to call a preset adoption model, calculate the adoption confidence of the output results, update the output result set in combination with the evaluation value, and select a new initial scheme from the output result set to input into the calculation model and obtain the output results again; wherein, the adoption model is pre-trained based on the adoption information of historical delivery schemes; The determining unit is used to filter output results that meet preset conditions from the result set in response to the termination command being triggered, so as to determine the delivery plan for the item.

8. The method according to claim 7, characterized in that, The update unit is specifically used for: A preset adoption model is invoked to calculate the adoption confidence score of the output result, and the total score of the output result is calculated based on the evaluation value and the adoption confidence score. In response to the total score satisfying the first condition, the output result is added to the output result set; If the total score does not meet the first condition, the output result is discarded.

9. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-6.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-6.

Images