Data return equipment determination method and device, storage medium and electronic equipment

Abstract

The invention relates to a determination method and device of data return equipment, a storage medium and electronic equipment. The method comprises the following steps: acquiring user feature data and data range information of each candidate device; determining affiliation relationship information of each screening condition in the user feature data and the data range information of each candidate device; based on the affiliation relationship information, deleting records corresponding to invalid conditions in the data range information to obtain target data range records, the invalid conditions being screening conditions not satisfied by the user feature data of the candidate devices; if the sum of weights corresponding to all screening conditions in the target data range record is greater than a preset value, randomly determining a target screening condition in the target data range record based on the weights; and determining a first preset number of target return devices corresponding to the target screening condition in the candidate devices based on the affiliation relationship information. The stability of the screening result of the return equipment can be guaranteed, and the expected effect of a user is better met.

Description

Technical Field

[0001] The present disclosure relates to the field of information technology, and in particular to a method, device, storage medium and electronic device for determining a data return device. Background Art

[0002] The screening process for the feedback device in the prior art is a binary filter. After the data is judged, there is only a yes or no result. The selected data cannot be configured with the sample ratio selected by each condition. The filter is uncontrollable. When the user's actual conversion data does not match the scenario, it may result in too little data that meets the conditions. In the flow delivery scenario, failure to meet the conversion number will affect the delivery effect. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned above, the present disclosure proposes a method, an apparatus, a storage medium and an electronic device for determining a data return device.

[0004] According to one aspect of the present disclosure, a method for determining a data backhaul device is provided, comprising:

[0005] Acquire user feature data and data range information of each candidate device, wherein the data range information includes at least one screening condition and its weight;

[0006] Determine the user characteristic data of each candidate device and the attribution relationship information of each screening condition in the data range information;

[0007] Based on the attribution relationship information, delete the record corresponding to the invalid condition in the data range information to obtain the target data range record, wherein the invalid condition is a screening condition that the user characteristic data of each candidate device does not satisfy;

[0008] If the sum of the weights corresponding to all the screening conditions in the target data range record is greater than a preset value, randomly determining the target screening condition in the target data range record based on the weight;

[0009] A first preset number of target return devices corresponding to the target screening condition in the candidate devices is determined based on the belonging relationship information.

[0010] In some possible implementations, the method further includes:

[0011] Obtain a second preset number of target return devices;

[0012] After determining a first preset number of target return devices corresponding to the target screening condition among the candidate devices based on the belonging relationship information, the method further includes:

[0013] Obtain the current number of the target return devices;

[0014] Determine the size of the second preset number and the current number;

[0015] If the second preset number is greater than the current number, deleting the target backhaul device from the candidate devices to obtain an updated candidate device;

[0016] Determining whether user characteristic data corresponding to the target screening condition exists in the updated candidate device based on the belonging relationship information;

[0017] If it does not exist, delete the record corresponding to the target screening condition in the target data range record to obtain an updated target data range record;

[0018] If the sum of the weights corresponding to all filtering conditions in the updated target data range record is greater than a preset value, repeat the steps of randomly determining the target filtering conditions in the target data range record based on the weights to determining the size of the second preset number and the current number.

[0019] In some possible implementations, the method further includes:

[0020] If so, repeat the steps of randomly determining the target screening condition in the target data range record based on the weight to determining the size of the second preset number and the current number.

[0021] In some possible implementations, the method further includes:

[0022] If the sum of the weights corresponding to all the screening conditions in the updated target data range record is a preset value, it is determined that there are the current number of target return devices among the candidate devices.

[0023] In some possible implementations, the method further includes:

[0024] If the sum of the weights corresponding to all the screening conditions in the target data range record is a preset value, it is determined that there is 0 target return device among the candidate devices.

[0025] In some possible implementations, the randomly determining the target screening condition in the target data range record based on the weight includes:

[0026] Determine probability information corresponding to each screening condition based on the weight corresponding to each screening condition in the target data range record;

[0027] Based on the probability information corresponding to each filtering condition, a filtering condition in the target data range record is randomly selected to obtain a target filtering condition.

[0028] In some possible implementations, the randomly determining the target screening condition in the target data range record based on the weight includes:

[0029] Mapping the weight corresponding to each screening condition in the target data range record to the first interval to obtain a target mapping relationship;

[0030] Randomly generate a target random number within the first interval;

[0031] The target screening condition is determined based on the target random number and the target mapping relationship.

[0032] According to a second aspect of the present disclosure, a device for determining a data backhaul device is provided, the device comprising:

[0033] A data acquisition module, used to acquire user feature data and data range information of each candidate device, wherein the data range information includes at least one screening condition and its weight;

[0034] An attribution relationship information determination module, used to determine the attribution relationship information of the user characteristic data of each candidate device and each screening condition in the data range information;

[0035] An invalid condition deletion module, used to delete the records corresponding to the invalid conditions in the data range information based on the belonging relationship information, and obtain the target data range records, wherein the invalid conditions are screening conditions that are not satisfied by the user characteristic data of each candidate device;

[0036] A target screening condition determination module, configured to randomly determine the target screening condition in the target data range record based on the weight if the sum of the weights corresponding to all the screening conditions in the target data range record is greater than a preset value;

[0037] The target backhaul device determination module is used to determine a first preset number of target backhaul devices corresponding to the target screening condition in the candidate devices based on the belonging relationship information.

[0038] According to a third aspect of the present disclosure, an electronic device is provided, comprising 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, and the at least one processor implements a method for determining a data return device as described in any one of the first aspects by executing the instructions stored in the memory.

[0039] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement a method for determining a data return device as described in any one of the first aspects.

[0040] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0041] The implementation of this disclosure has the following beneficial effects:

[0042] Obtain user feature data and data range information of each candidate device, the data range information includes at least one screening condition and its weight; determine the attribution relationship information of each screening condition in the user feature data and data range information of each candidate device; classify the candidate devices according to the screening conditions first, and determine the screening conditions satisfied by the devices; delete the records corresponding to the invalid conditions in the data range information based on the attribution relationship information, and obtain the target data range record, the invalid conditions are the screening conditions that the user feature data of each candidate device do not satisfy; when there is no data matching the harsh condition, the selection probability of this condition will be automatically removed, even if the weight set for this condition is high, so as to facilitate the random selection of the screening conditions below; if the sum of the weights corresponding to all the screening conditions in the target data range record is greater than the preset value, the target screening condition in the target data range record is randomly determined based on the weight; determine the first preset number of target return devices corresponding to the target screening condition in the candidate device based on the attribution relationship information. Randomly select each screening condition based on its weight in the first target data range, so that the selected target screening condition tends to the set weight, but does not completely rely on the weight, to ensure the stability of the screening result.

[0043] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments or prior art descriptions. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A schematic diagram showing a flow chart of a method for determining a data backhaul device according to an embodiment of the present disclosure;

[0046] Figure 2A schematic diagram showing a flow chart of a method for determining a first cycle of a target backhaul device according to an embodiment of the present disclosure;

[0047] Figure 3 A schematic diagram showing a flow chart of a method for determining a second cycle of a target backhaul device according to an embodiment of the present disclosure;

[0048] Figure 4 A schematic diagram showing a flow chart of a first method for determining the current number of target backhaul devices according to an embodiment of the present disclosure;

[0049] Figure 5 A schematic diagram showing a flow chart of a method for determining 0 target backhaul devices according to an embodiment of the present disclosure;

[0050] Figure 6 A schematic diagram showing a flow chart of a method for randomly determining target screening conditions based on probability according to an embodiment of the present disclosure;

[0051] Figure 7 A schematic diagram showing a flow chart of a method for determining target screening conditions based on random data according to an embodiment of the present disclosure;

[0052] Figure 8 A schematic diagram showing the structure of a determination device of a data backhaul device according to an embodiment of the present disclosure;

[0053] Fig. 9 A block diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0056] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0057] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0058] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0059] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0060] Figure 1 A flow chart showing a method for determining a data backhaul device according to an embodiment of the present disclosure is shown as follows: Figure 1 As shown, the above method includes:

[0061] S101, obtaining user feature data and data range information of each candidate device, where the data range information includes at least one screening condition and its weight;

[0062] The executor of this solution can be a server, and the candidate devices include but are not limited to handheld computers, desktop computers, mobile phones, media players, personal digital assistants, and various combinations of the aforementioned devices. The candidate devices are devices identified by the server, and the user feature data are data streams sent by the candidate devices. The data range information includes preset filtering conditions and weights corresponding to the filtering conditions. The weight is used to characterize the degree to which the candidate devices that meet the filtering conditions are expected to be selected. If the weight corresponding to the filtering conditions is 0, it means that the candidate devices that meet the filtering conditions do not want to be selected.

[0063] The data range information may be one or more screening conditions pre-set by the user according to actual conditions, and the expected degree of selection corresponding to each screening condition, ie, the weight, is set.

[0064] In some embodiments, the server recognizes 10 devices flowing in and uses the 10 devices as candidate devices. The data range information is set to include condition 1, weight 10; condition 2, weight 30; condition 3, weight 40; condition 4, weight 0; condition 5, weight 20.

[0065] S102: Determine the attribution relationship information of each screening condition in the user feature data and data range information of each candidate device.

[0066] Determine the candidate devices that meet each screening condition, that is, divide the candidate devices based on the candidate conditions to obtain the attribution relationship information. If there is a candidate device that does not meet any screening condition among the candidate devices, it will not be considered.

[0067] In some embodiments, the attribution relationship information is condition one: device 2; condition two: device 3, device 5; condition three: device 7, device 9; condition four: device 1, device 4, device 6, device 8, device 10; condition five: none.

[0068] S103, deleting records corresponding to invalid conditions in the data range information based on the belonging relationship information to obtain target data range records, where the invalid conditions are screening conditions that are not satisfied by the user characteristic data of each candidate device;

[0069] If no candidate device satisfies a certain filtering condition in the data range information, the filtering condition is confirmed to be an invalid condition, and the invalid condition in the data range information is deleted to ensure that all the filtering conditions in the data range information have corresponding candidate devices.

[0070] In some embodiments, there is no device satisfying condition five in the data range information among the candidate devices, and the record corresponding to condition five in the preset range information is deleted.

[0071] S104: If the sum of the weights corresponding to all the screening conditions in the target data range record is greater than a preset value, randomly determine the target screening condition in the target data range record based on the weight;

[0072] The preset value can be 0. The weights corresponding to the filtering conditions in the target data range record are summed to obtain the target weight value. If the target weight value is greater than 0, a random algorithm with weights is used to extract a filtering condition in the target data range record as the target filtering condition.

[0073] In some embodiments, the filter conditions in the target data range record may be placed in a roulette wheel, and the area of ​​each filter condition may be allocated based on the weight, and one of the filter conditions may be selected as the target filter condition in a roulette wheel manner.

[0074] In some embodiments, if the target data range is recorded as: condition one, weight is 10; condition two, weight is 30; condition three, weight is 40; condition four, weight is 0; the probability of each condition being selected is condition one: 10 / (10+30+40), condition two: 30 / (10+30+40), condition three: 40 / (10+30+40), condition four: 0 / (10+30+40), and random selection is performed based on the probability of each condition. Condition three has the largest probability and a higher probability of being selected.

[0075] S105: Determine a first preset number of target return devices corresponding to the target screening condition from the candidate devices based on the belonging relationship information.

[0076] The first preset number may be 1, that is, one target return device is selected each time. Candidate devices corresponding to the target screening condition are determined according to the attribution relationship information, and one device is selected from the candidate devices corresponding to the target screening condition as the target return device to realize data return.

[0077] In some embodiments, if the target screening condition randomly selected based on probability is condition three with a probability of 1 / 2, the candidate devices corresponding to condition three are device 7 and device 9. At this time, any device is selected from device 7 and device 9 as the target return device to return data.

[0078] The above technical solution can configure multiple screening conditions and their weights as needed. When the data in the circle meets multiple conditions, the candidate devices that meet the conditions are selected according to the weight probability set for the conditions. The screening of candidate devices is determined by multiplying the number of actual conditions and the weight. When no data matches the more stringent conditions, the selection probability of this condition is automatically removed, even if the weight set for this condition is higher. In the screening scenario where the number of selections is determined, the weight corresponding to each screening condition is randomly selected, so that the selected target screening condition tends to the set weight, but does not rely entirely on the weight, to ensure the stability of the screening results.

[0079] In some embodiments, the method further comprises:

[0080] Obtain a second preset number of target return devices;

[0081] The number of devices that need to transmit data back is obtained, that is, the second preset number of target transmission devices, and the second preset number is set according to user needs.

[0082] Exemplarily, the second preset number of target backhaul devices may be three.

[0083] See also Figure 2After determining a first preset number of target return devices corresponding to the target screening condition in the candidate devices based on the belonging relationship information, the method further includes:

[0084] S201, obtaining the current number of target backhaul devices;

[0085] S202, determining the size of the second preset quantity and the current quantity;

[0086] S203: If the second preset number is greater than the current number, delete the target backhaul device from the candidate devices to obtain an updated candidate device;

[0087] S204, judging whether there is user characteristic data corresponding to the target screening condition in the updated candidate device based on the ownership relationship information;

[0088] S205. If it does not exist, delete the record corresponding to the target screening condition in the target data range record to obtain an updated target data range record;

[0089] S206: If the sum of the weights corresponding to all the screening conditions in the updated target data range record is greater than the preset value, repeat the step of randomly determining the target screening conditions in the target data range record based on the weights to determine the size of the second preset number and the current number.

[0090] After selecting the first preset number of target return devices at one time, the number of selected target return devices is obtained. For example, the first preset number is 1, and only one target return device is selected in each round. If two rounds of target return device selection have been carried out, the current number of target return devices is 2; if the second preset number is 3, and the number of the second preset number is greater than the current number, then the target return devices selected in the previous round are deleted from the candidate devices, and the selection of a new round of target return devices continues.

[0091] Since one of the candidate devices corresponding to the target filtering condition has been selected as the target return device, it is determined again based on the attribution information whether the user feature data corresponding to the target filtering condition still exists in the updated candidate device. If not, the record corresponding to the target filtering condition is deleted to obtain the updated target data range record. Continue to determine whether the sum of the weights corresponding to all the filtering conditions in the updated target data range record is greater than the preset value. Exemplarily, the preset value can be 0. If it is equal to the preset value, it means that the weights of the remaining filtering conditions in the updated target data range record are all 0, that is, none of them want to be selected, or the filtering conditions in the updated target data range record are deleted because there is no corresponding candidate device. If the sum of the weights corresponding to all the filtering conditions in the updated target data range record is greater than the preset value, repeat the steps of randomly determining the target filtering conditions in the target data range record based on the weight to determining the size of the second preset number and the current number, that is, a new round of target return device selection is performed.

[0092] In some embodiments, the target data range record is: condition one, weight is 10; condition two, weight is 30; condition three, weight is 40; condition four, weight is 0; the ownership relationship information is: condition one: device 2; condition two: device 3, device 5; condition three: device 7, device 9; condition four: device 1, device 4, device 6, device 8, device 10; if the target screening condition selected in the first round is condition three, and the determined target return device is device 7 under condition three, then the relevant records of device 7 are deleted from the candidate devices. If the target screening condition selected in the second round is still condition three, and the selected target return device is device 9, continue to delete the relevant information of device 9 in the candidate devices. At this time, the device corresponding to condition three does not exist in the updated candidate devices. Therefore, in the confirmation process of the target return device in the third round, the record corresponding to condition three in the target data range record is deleted.

[0093] In the above technical solution, the data screening is determined by multiplying the data volume and weight of the candidate devices that actually meet the conditions. When no candidate device matches a more stringent condition, the selection probability of this condition is automatically removed, even if the weight set for this condition is higher.

[0094] See also Figure 3 In some embodiments, the method further comprises:

[0095] S301, if it exists, repeatedly executing the step of randomly determining the target screening condition in the target data range record based on the weight to determining the size of the second preset number and the current number.

[0096] If the updated candidate devices still have user feature data corresponding to the target screening condition, a screening condition is randomly selected as the target screening condition based on the weights corresponding to the screening conditions in the target data range record, and a first preset number of target return devices of the candidate devices corresponding to the target screening condition are randomly selected. Continue to determine whether the total number of target return devices meets the second preset number. If so, stop selecting the target return devices. If not, continue to determine the next round of target return devices according to the original logic.

[0097] In the above technical solution, when confirming the target backhaul device for the next round, it is necessary to remove the selected devices and repeat the weighted random selection according to the original logic until enough backhaul devices are selected.

[0098] See also Figure 4 In some embodiments, the method further comprises:

[0099] S401: If the sum of the weights corresponding to all the screening conditions in the updated target data range record is a preset value, it is determined that there are the current number of target return devices among the candidate devices.

[0100] The preset value may be 0. The weights corresponding to the filter conditions in the updated target data range record are summed. When the result is 0, it indicates that there is no filter condition that is expected to be selected. At this time, the target return device is stopped from being selected.

[0101] In some embodiments, if the expected number of target return devices is 10, that is, the second preset number is 10, after the fifth device is selected, that is, the current number is 5, the remaining candidate devices are device 1, device 4, device 6, device 8, and device 10, and the updated target data range record is: condition four, weight is 0; the belonging relationship information is: condition one: device 2; condition two: device 3, device 5; condition three: device 7, device 9; condition four: device 1, device 4, device 6, device 8, device 10; at this time, the weight corresponding to the screening condition of the updated target data range record is 0. At this time, stop the continued selection of the target return device, determine that the final number of target return devices is 5, and return data to these 5 target return devices.

[0102] In the above technical solution, when you do not want to select data of a certain filtering condition at all, you can set its weight to 0, and then the device corresponding to the filtering condition will not be selected at all.

[0103] See also Figure 5 In some embodiments, the method further comprises:

[0104] S501: If the sum of the weights corresponding to all the screening conditions in the target data range record is a preset value, it is determined that there is 0 target return device among the candidate devices.

[0105] If the records corresponding to the invalid conditions in the data range information are deleted based on the attribution relationship information, after the target data range record is obtained, the sum of the weights corresponding to the filtering conditions in the target data range record is 0, and it is determined that none of the candidate devices corresponding to the filtering conditions in the target data range record want to be selected. At this time, the target return device selection process is exited, and the selected target return device is determined to be 0.

[0106] In the above technical solution, when you do not want to select data of certain filtering conditions at all, you can set their weights to 0, and then the devices corresponding to these filtering conditions will not be selected at all.

[0107] See also Figure 6 In some embodiments, the target filtering condition in the target data range record is randomly determined based on the weight, including:

[0108] S601, determining probability information corresponding to each screening condition based on the weight corresponding to each screening condition in the target data range record;

[0109] S602: Randomly select a filtering condition in the target data range record based on the probability information corresponding to each filtering condition to obtain a target filtering condition.

[0110] The probability corresponding to each filtering condition is calculated according to the weight corresponding to each filtering condition in the target data range record. The greater the probability of the filtering condition, the greater the probability of being randomly selected. Conversely, the smaller the probability of the filtering condition, the smaller the probability of being randomly selected. The filtering condition with a weight of 0, that is, a probability of 0, will not be selected.

[0111] In some embodiments, the probability corresponding to each screening condition is the weight of the screening condition divided by the sum of the weights of all screening conditions. The target screening condition is determined using a weighted random algorithm and probability information.

[0112] The above technical solution, based on probability-based conditional screening, is more suitable for advertising delivery scenarios, can control the distribution of the conversion population, and meets the user's expected effects.

[0113] See also Figure 7 In some embodiments, the target filtering condition in the target data range record is randomly determined based on the weight, including:

[0114] S701, mapping the weight corresponding to each screening condition in the target data range record to the first interval to obtain a target mapping relationship;

[0115] S702, randomly generate a target random number within a first interval;

[0116] S703: Determine a target screening condition based on the target random number and the target mapping relationship.

[0117] In some embodiments, after probability calculation of the weight corresponding to each filtering condition in the target data range record, the weight is distributed to the interval [0,1], and a random number between [0,1] is randomly generated. The interval corresponding to which the random number belongs is the target filtering condition corresponding to the weight.

[0118] In some embodiments, the target data range is recorded as follows: condition one, weight is 10; condition two, weight is 30; condition three, weight is 40; condition four, weight is 0; the probability of each condition being selected is condition one: 10 / (10+30+40), condition two: 30 / (10+30+40), condition three: 40 / (10+30+40), condition four: 0 / (10+30+40), accordingly, condition one occupies the interval [0,1] in [0,1] +30+40)], condition two occupies the interval [10 / (10+30+40),(10+30) / (10+30+40)] in [0,1], condition three occupies the interval [(10+30) / (10+30+40),(10+30+40) / (10+30+40)] in [0,1]. Randomly generate a random number between [0,1]. If the random number is 3 / 4, the random number belongs to the space occupied by condition three. Therefore, condition three belongs to the target screening condition.

[0119] The above technical solution is based on random selection based on weights. If the sample data conversion rate is good, some low-quality data can be mixed in. If the sample data conversion rate is not good, it can also ensure that all high-quality data can be retrieved first, avoiding frequent changes in conditions due to actual sampling data not meeting expectations.

[0120] See also Figure 8 According to a second aspect of the present disclosure, a device for determining a data backhaul device is provided, the device comprising:

[0121] A data acquisition module 10, used to acquire user feature data and data range information of each candidate device, where the data range information includes at least one screening condition and its weight;

[0122] The attribution relationship information determination module 20 is used to determine the attribution relationship information of each screening condition in the user characteristic data and data range information of each candidate device;

[0123] The invalid condition deletion module 30 is used to delete the records corresponding to the invalid conditions in the data range information based on the belonging relationship information to obtain the target data range records, where the invalid conditions are the screening conditions that the user characteristic data of each candidate device does not satisfy;

[0124] A target screening condition determination module 40, configured to randomly determine a target screening condition in the target data range record based on the weight if the sum of the weights corresponding to all screening conditions in the target data range record is greater than a preset value;

[0125] The target backhaul device determination module 50 is used to determine a first preset number of target backhaul devices corresponding to the target screening condition in the candidate devices based on the belonging relationship information.

[0126] In some embodiments, the apparatus further comprises:

[0127] A second preset number acquisition module, used to acquire a second preset number of target backhaul devices;

[0128] The device also includes:

[0129] The current number acquisition module is used to obtain the current number of target return devices;

[0130] A determination module, used for determining the size of the second preset quantity and the current quantity;

[0131] A first updating module, configured to delete the target backhaul device from the candidate devices if the second preset number is greater than the current number, to obtain an updated candidate device;

[0132] A second updating module, configured to determine whether user characteristic data corresponding to the target screening condition exists in the updated candidate device based on the belonging relationship information;

[0133] A third updating module is used to delete the record corresponding to the target screening condition in the target data range record if it does not exist, and obtain an updated target data range record;

[0134] The first loop module is used to repeatedly execute the steps of randomly determining the target filtering conditions in the target data range record based on the weight to determine the size of the second preset number and the current number if the sum of the weights corresponding to all filtering conditions in the updated target data range record is greater than the preset value.

[0135] In some embodiments, the apparatus further comprises:

[0136] The second loop module is used to repeatedly execute the steps of randomly determining the target screening condition in the target data range record based on the weight to determining the size of the second preset number and the current number, if any.

[0137] In some embodiments, the apparatus further comprises:

[0138] The first module for determining the number of target return devices is used to determine that there are the current number of target return devices among the candidate devices if the sum of the weights corresponding to all the screening conditions in the updated target data range record is a preset value.

[0139] In some embodiments, the apparatus further comprises:

[0140] The second module for determining the number of target return devices is used to determine that there are 0 target return devices among the candidate devices if the sum of the weights corresponding to all the screening conditions in the target data range record is a preset value.

[0141] In some embodiments, the target screening condition determination module 40 includes:

[0142] A probability information determination unit, configured to determine probability information corresponding to each screening condition based on a weight corresponding to each screening condition in the target data range record;

[0143] The first screening condition determination unit is used to randomly select a screening condition in the target data range record based on the probability information corresponding to each screening condition to obtain a target screening condition.

[0144] In some embodiments, the target screening condition determination module 40 includes:

[0145] A mapping unit, used to map the weight corresponding to each screening condition in the target data range record to the first interval to obtain a target mapping relationship;

[0146] A random number generating unit, used for randomly generating a target random number within a first interval;

[0147] The second screening condition determination unit is used to determine the target screening condition based on the target random number and the target mapping relationship.

[0148] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0149] An embodiment of the present application provides a determination device for a data return device, which may be a terminal or a server. The determination device for the data return device includes a processor and a memory, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by the processor to implement a determination method for a data return device as provided in the above method embodiment.

[0150] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0151] The method embodiments provided in the embodiments of the present application can be executed in electronic devices such as mobile terminals, computer terminals, servers or similar computing devices. Fig. 9 1 is a hardware structure block diagram of an electronic device for determining a data return device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device 900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 910 (the processor 910 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 930 for storing data, and one or more storage media 920 (such as one or more mass storage devices) for storing application programs 923 or data 922. Among them, the memory 930 and the storage medium 920 can be short-term storage or permanent storage. The program stored in the storage medium 920 may include one or more modules, and each module may include a series of instruction operations in the electronic device. Furthermore, the central processing unit 910 can be configured to communicate with the storage medium 920 to execute a series of instruction operations in the storage medium 920 on the electronic device 900. The electronic device 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input and output interfaces 940, and / or one or more operating systems 921, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0152] The input / output interface 940 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the electronic device 900. In one example, the input / output interface 940 includes a network adapter (NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 940 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0153] It can be understood by those skilled in the art that Fig. 9 The structure shown is only for illustration and does not limit the structure of the above electronic device. Fig. 9 More or fewer components as shown, or with Fig. 9 Different configurations shown.

[0154] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to a method for determining a data return device in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method for determining a data return device provided in the above method embodiment.

[0155] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0156] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0157] It can be seen from the embodiments of the method, apparatus, device, terminal, server, storage medium or computer program for determining the data return device provided by the present application that the present application obtains user feature data and data range information of each candidate device, the data range information including at least one screening condition and its weight; determines the attribution information of each screening condition in the user feature data and data range information of each candidate device; classifies the candidate devices according to the screening conditions to determine the screening conditions satisfied by the devices; deletes the records corresponding to the invalid conditions in the data range information based on the attribution information to obtain the target data range record, the invalid conditions being the screening conditions that are not satisfied by the user feature data of each candidate device; when no data matches the harsh condition, the selection probability of this condition will be automatically removed, even if the weight set for this condition is high, so as to facilitate the random selection of the screening condition below; if the sum of the weights corresponding to all the screening conditions in the target data range record is greater than the preset value, the target screening condition in the target data range record is randomly determined based on the weight; and the first preset number of target return devices corresponding to the target screening condition in the candidate device is determined based on the attribution information. Each screening condition in the first target data range is randomly selected based on its corresponding weight, so that the selected target screening condition tends to the set weight, but does not completely rely on the weight, thereby ensuring the stability of the screening result quantity.

[0158] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0160] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0161] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for determining a data return device, characterized in that: The method comprises: Acquire user feature data and data range information of each candidate device, wherein the data range information includes at least one screening condition and its weight; Determine the user characteristic data of each candidate device and the attribution relationship information of each screening condition in the data range information; Based on the attribution relationship information, delete the record corresponding to the invalid condition in the data range information to obtain the target data range record, wherein the invalid condition is a screening condition that the user characteristic data of each candidate device does not satisfy; If the sum of the weights corresponding to all the screening conditions in the target data range record is greater than a preset value, randomly determining the target screening condition in the target data range record based on the weight; A first preset number of target return devices corresponding to the target screening condition in the candidate devices is determined based on the belonging relationship information.

2. The method according to claim 1, characterized in that: The method further comprises: Obtain a second preset number of target return devices; After determining a first preset number of target return devices corresponding to the target screening condition among the candidate devices based on the belonging relationship information, the method further includes: Obtain the current number of the target return devices; Determine the size of the second preset number and the current number; If the second preset number is greater than the current number, deleting the target backhaul device from the candidate devices to obtain an updated candidate device; Determining whether user characteristic data corresponding to the target screening condition exists in the updated candidate device based on the belonging relationship information; If it does not exist, delete the record corresponding to the target screening condition in the target data range record to obtain an updated target data range record; If the sum of the weights corresponding to all filtering conditions in the updated target data range record is greater than a preset value, repeat the steps of randomly determining the target filtering conditions in the target data range record based on the weights to determining the size of the second preset number and the current number.

3. The method according to claim 2, characterized in that The method further comprises: If so, repeat the steps of randomly determining the target screening condition in the target data range record based on the weight to determining the size of the second preset number and the current number.

4. The method according to claim 2, characterized in that: The method further comprises: If the sum of the weights corresponding to all the screening conditions in the updated target data range record is a preset value, it is determined that there are the current number of target return devices among the candidate devices.

5. The method according to claim 1, characterized in that: The method further comprises: If the sum of the weights corresponding to all the screening conditions in the target data range record is a preset value, it is determined that there is 0 target return device among the candidate devices.

6. The method according to claim 1, characterized in that The randomly determining the target screening condition in the target data range record based on the weight includes: Determine probability information corresponding to each screening condition based on the weight corresponding to each screening condition in the target data range record; Based on the probability information corresponding to each filtering condition, a filtering condition in the target data range record is randomly selected to obtain a target filtering condition.

7. The method according to claim 1, characterized in that The randomly determining the target screening condition in the target data range record based on the weight includes: Mapping the weight corresponding to each screening condition in the target data range record to the first interval to obtain a target mapping relationship; Randomly generate a target random number within the first interval; The target screening condition is determined based on the target random number and the target mapping relationship.

8. A device for determining a data return device, characterized in that: The device comprises: A data acquisition module, used to acquire user feature data and data range information of each candidate device, wherein the data range information includes at least one screening condition and its weight; An attribution relationship information determination module, used to determine the attribution relationship information of the user characteristic data of each candidate device and each screening condition in the data range information; An invalid condition deletion module, used to delete the records corresponding to the invalid conditions in the data range information based on the belonging relationship information, and obtain the target data range records, wherein the invalid conditions are screening conditions that are not satisfied by the user characteristic data of each candidate device; A target screening condition determination module, configured to randomly determine the target screening condition in the target data range record based on the weight if the sum of the weights corresponding to all the screening conditions in the target data range record is greater than a preset value; The target backhaul device determination module is used to determine a first preset number of target backhaul devices corresponding to the target screening condition in the candidate devices based on the belonging relationship information.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the determination method of the data return device as described in any one of claims 1-7.

10. An electronic device, characterized in that: It includes at least one processor and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the determination method of the data return device as described in any one of claims 1 to 7 by executing the instructions stored in the memory.

Images