Offline content delivery method, device and equipment based on payment device

Abstract

The embodiments of this specification disclose offline content delivery methods, devices and equipment based on payment collection devices. The scheme includes: receiving a delivery request form sent by the delivery end of the first merchant; screening multiple payment collection devices of second merchants that can receive orders around the delivery end to form a first set of devices; determining multiple fine screening dimensions based on a pre-constructed merchant-related data set, and determining the performance data of each first payment collection device in the first set of devices on the fine screening dimensions; determining a differentiated dimension effect prediction scheme based on the relationship type between each fine screening dimension and the delivery effect, and predicting multiple fine screening dimension scores for each first payment collection device based on the performance data; determining the ranking scores of each first payment collection device based on the multiple fine screening dimension scores of each first payment collection device; screening a part of the first payment collection devices based on the ranking scores to form a second set of devices; determining the delivery device of the offline content of the delivery request form in the second set of devices, and performing corresponding delivery.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to offline content delivery methods, devices and equipment based on payment devices. Background Art

[0002] With the development of computer and Internet technology, content released by merchants can be seen in more and more offline scenarios.

[0003] In the traditional offline content delivery process, the information held by the delivery owner and the device owner is not equal. Both parties need to find business opportunities on their own and rely on human experience to determine the future delivery effect. In addition, the devices owned by the device owner are usually dedicated devices for content delivery (such as advertising machines, large LED screens, etc.), and their application scenarios are often relatively fixed. For example, they are used in subway stations, bus stations, office buildings and other scenarios. Users will not pay special attention to the content they deliver, and due to reasons such as site rental and equipment maintenance, their delivery costs are relatively high.

[0004] Based on this, a solution that can better guarantee the effectiveness of offline content delivery is needed. Summary of the invention

[0005] One or more embodiments of this specification provide an offline content delivery method, apparatus, device, and storage medium based on a payment device to solve the following technical problem: a solution that can better guarantee the effect of offline content delivery is needed.

[0006] To solve the above technical problems, one or more embodiments of this specification are implemented as follows:

[0007] One or more embodiments of this specification provide an offline content delivery method based on a payment device, including:

[0008] Receiving a delivery request form sent by the delivery terminal of the first merchant;

[0009] Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices;

[0010] Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0011] Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predict a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0012] Determine the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0013] According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices;

[0014] Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0015] One or more embodiments of this specification provide an offline content delivery device based on a payment device, including:

[0016] A receiving module receives a delivery request form sent by a delivery terminal of the first merchant;

[0017] A first screening module is configured to screen payment collection devices of a plurality of second merchants that are located around the delivery end and can receive orders, so as to form a first set of devices;

[0018] a performance data determination module, which determines a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determines the performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0019] A prediction module, which determines a differentiated dimension effect prediction scheme according to the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predicts a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0020] A ranking score determination module, which determines the ranking scores of each of the first payment receiving devices according to the multiple fine screening dimension scores of each of the first payment receiving devices;

[0021] A second screening module, screening a portion of the first payment receiving devices according to the ranking scores to form a second set of devices;

[0022] The delivery module determines the delivery device of the offline content of the delivery request form in the second set of devices, and performs corresponding delivery.

[0023] One or more embodiments of this specification provide an offline content delivery device based on a payment device, including:

[0024] at least one processor; and,

[0025] a memory communicatively connected to the at least one processor; wherein,

[0026] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0027] Receiving a delivery request form sent by the delivery terminal of the first merchant;

[0028] Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices;

[0029] Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0030] Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predict a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0031] Determine the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0032] According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices;

[0033] Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0034] One or more embodiments of this specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to:

[0035] Receiving a delivery request form sent by the delivery terminal of the first merchant;

[0036] Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices;

[0037] Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0038] Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predict a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0039] Determine the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0040] According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices;

[0041] Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0042] At least one of the above technical solutions adopted in one or more embodiments of this specification can achieve the following beneficial effects:

[0043] Compared with dedicated delivery devices, payment collection devices have a wider range of application scenarios, and they attract more attention from users who want to perform payment services, which can bring better delivery effects to the first merchant. In addition, payment collection devices are usually small in size and can be used after being installed in various merchant stores, saving site fees and requiring no special maintenance, reducing the cost required for the first merchant to deliver offline content, while the second merchant can also increase its own revenue by delivering offline content, achieving the effect of diversified use of payment collection devices and achieving a win-win situation for both parties.

[0044] By setting multiple fine screening dimensions and adopting differentiated dimensional effect prediction schemes for different payment collection devices, the ranking scores of each payment collection device are predicted, and the most suitable payment collection device is selected for the delivery end based on the predicted ranking scores, thus ensuring the final delivery effect and the profits of the delivery owner and the device owner. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 A flowchart of an offline content delivery method based on a payment device provided in one or more embodiments of this specification;

[0047] Figure 2 A schematic diagram of a framework of an offline content delivery system based on a payment device provided in one or more embodiments of this specification;

[0048] Figure 3 A schematic diagram of a process of recalling a payment device in an offline content delivery method based on a payment device provided in one or more embodiments of this specification;

[0049] Figure 4 A schematic diagram of the structure of an offline content delivery device based on a payment device provided in one or more embodiments of this specification;

[0050] Figure 5 A schematic diagram of the structure of an offline content delivery device based on a payment device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0051] The embodiments of this specification provide an offline content delivery method, apparatus, device and storage medium based on a payment device.

[0052] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0053] Figure 1 A flow chart of a method for offline content delivery based on a payment device on the server side provided for one or more embodiments of this specification. The method can be applied to different business fields, such as offline payment field, Internet financial business field, e-commerce business field, instant messaging business field, game business field, official business field, etc. The process can be executed by a computing device in the corresponding field (such as a server corresponding to an offline payment business, a payment device, etc.), and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy.

[0054] Figure 1 The process in may include the following steps:

[0055] S102: Receive a delivery request form sent by the delivery end of the first merchant.

[0056] Figure 2 A schematic diagram of a framework of an offline content delivery system based on a payment device provided for one or more embodiments of this specification. When a merchant has a demand for content delivery (hereinafter referred to as the first merchant or delivery host), the first merchant sends a delivery request to the server through a corresponding device (hereinafter referred to as the delivery end). The delivery request carries the delivery demand of the first merchant. The delivery demand directly or indirectly expresses the offline content that the first merchant wants to deliver this time and the selected delivery package (including the delivery days, the number of delivery devices, etc.). For example, the delivery demand can be a video, poster, audio that can be directly used for offline content delivery, or a text description that reflects the requirements of the first merchant. The server or a third party makes content that can be directly delivered based on the text description. The delivery end can be a terminal device with corresponding functions such as a mobile phone, a personal PC, and a payment device.

[0057] S104: Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders, to form a first set of devices.

[0058] There are many types of payment devices, which can perform payment services based on QR codes, credit cards, etc. For example, users complete payment by showing their payment codes to the payment device, scanning the payment codes displayed by the payment device, swiping the card on the payment device, etc. The merchant that owns the payment device is referred to as the second merchant or device owner.

[0059] If after receiving the delivery request, the delivery is carried out through traditional delivery methods, relying on manual experience or indiscriminate selection of payment devices, it is easy to make the final delivery effect poor, which will affect the interests of the delivery owner and the device owner. For offline content delivery, the first merchant usually pays attention to the location of the payment device, hoping that the payment device can be closer to its own store, so that when potential users see the offline content delivered on the payment device, they can quickly reach the store where the first merchant is located. Even when the first merchant is close enough to the payment device, when the user sees the offline content delivered from the payment device, he can see the store of the first merchant as soon as he looks up. At this time, for the user, it only takes a few steps to reach the first merchant. If he is interested in the offline content delivered, there is a high probability that he will go to the first merchant.

[0060] Based on this, the location of the first merchant store is determined by the location information of the delivery end. However, since the delivery end may be a movable device, its location information may change due to the movement of the delivery owner. Therefore, the location information of the delivery end may not be determined by the terminal positioning method, but by the delivery owner. Determine whether the payment device is located around the delivery end based on the location information of the delivery end and each payment device (whether it is located around can be determined based on a preset distance, for example, the surrounding can refer to payment devices within a radius of 2 kilometers near the delivery end). For example, the distance between the delivery end and each payment device is determined through the location-based services (LBS) coordinates of the delivery end and each payment device, and then determine whether the payment device is located around the delivery end.

[0061] Of course, to ensure the experience of the second merchant, in the process of building the first set of devices, only the second merchant that can accept orders will be selected for payment devices. Whether it is in the state of being able to accept orders is chosen by the second merchant, and it can be changed based on its own needs and actual conditions. At this time, both the first merchant and the second merchant have expressed their willingness to deliver offline content, and the server plays a more matchmaking role, bringing the first merchant and the second merchant together to achieve a win-win situation for both parties.

[0062] S106: Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions.

[0063] The merchant-related data set includes relevant data corresponding to the first merchant and the second merchant respectively. The relevant data may include merchant information (for example, location information, delivery end information, payment device information, etc.), transaction information (for example, transaction business field, transaction volume, etc.), historical offline content delivery information, etc., which can be stored in the form of a knowledge graph.

[0064] Figure 3 A schematic diagram of a payment device recall process in an offline content delivery method based on a payment device provided in one or more embodiments of this specification, wherein Figure 3 In the figure, three fine screening dimensions are used as examples for illustration. Fine screening dimensions refer to the preset dimensions for screening payment devices. The performance data can reflect the relevant performance of the payment devices in the first set of devices (for the convenience of description, the payment devices in the first set of devices are referred to as the first payment devices) under this fine screening dimension. Performance data can be reflected in a variety of ways based on different fine screening dimensions. For example, for the dimension of distance, the distance between the payment device and the area to which the delivery end belongs can be used as performance data. For the dimension of transaction volume, the transaction volume or transaction amount of the payment device in the corresponding time period can be used as performance data.

[0065] S108: Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine-screening dimensions and the delivery effect, and accordingly predict a plurality of fine-screening dimension scores for each of the first payment devices in combination with the performance data.

[0066] The delivery effect refers to the positive effect brought to the delivery end, which may include economic benefits, user attention, visit volume, topic volume, etc., and can be used to determine which delivery effects the first merchant is more concerned about based on the delivery requirements in the delivery request form, so as to conduct more targeted screening of payment devices. The delivery effect here is not the actual delivery effect after the offline content delivery this time, but mainly refers to the estimated delivery effect of the offline content this time through manual experience, historical data analysis, related algorithms, etc., combined with the performance data of the first payment device.

[0067] There are many types of relationships, such as positive correlation (as the performance data increases, the delivery effect increases), negative correlation (as the performance data increases, the delivery effect decreases), periodicity (as the performance data continues to change, the delivery effect changes periodically), mutation (as the performance data continues to change, the delivery effect will continue to change suddenly), discrete (only partial changes in performance data can affect the delivery effect), etc. Of course, the relationship types can be further divided here to obtain more precise relationship types, for example, the positive correlation type can be further divided into linear positive correlation type, nonlinear positive correlation type, etc.

[0068] The differentiated dimensional effect prediction scheme refers to a prediction scheme under the corresponding dimension obtained by executing differentiated settings according to different relationship types, which includes predictions through pre-trained models, pre-set formulas, human experience, etc.

[0069] like Figure 3 As shown, the fine screening dimension score is obtained by analyzing and predicting the input performance data under the fine screening dimension through its corresponding differentiated dimension effect prediction scheme. The fine screening dimension score can reflect the degree of influence of the payment collection device on the delivery effect under the fine screening dimension. Generally speaking, the higher the fine screening dimension score, the better the delivery effect of the payment collection device.

[0070] S110: Determine the ranking scores of each of the first payment receiving devices according to the multiple fine screening dimension scores of each of the first payment receiving devices.

[0071] like Figure 3 As shown, for each first payment collection device, it corresponds to multiple fine screening dimensions, and naturally multiple fine screening dimension scores can be obtained. After comprehensive processing of these multiple fine screening dimension scores, they are sorted according to the scores to obtain the ranking score. The fine screening dimension score can only reflect the delivery effect that the payment collection device can achieve under a single fine screening dimension, while the ranking score can reflect the more complete delivery effect that the payment collection device can achieve under all fine screening dimensions.

[0072] Specifically, the comprehensive process can be carried out in a variety of ways, for example, according to the preset weights of each fine screening dimension and the corresponding fine screening dimension scores, the ranking scores are obtained by weighting. Alternatively, according to the delivery requirements in the delivery request form, some fine screening dimensions are selected to obtain the ranking scores.

[0073] S112: Filter a portion of the first payment receiving devices according to the ranking scores to form a second set of devices.

[0074] In the screening process of the first payment collection devices, a part of the first payment collection devices with the highest ranking scores are usually selected to form the second set of devices, thereby bringing the best delivery effect to the first merchant. However, in some special cases, such as reasons on the delivery side (the selected package is a low-level package, and there is a concern that the traffic is too large to make it difficult to supply the goods), reasons on the first payment collection device side (the offline content delivery of several first payment collection devices with the highest ranking scores has been saturated), etc., at this time, some first payment collection devices with lower ranking scores will be selected to form the second set of devices, but first payment collection devices with the highest ranking scores as possible will still be selected to ensure the interests of the first merchant.

[0075] S114: Determine the delivery device for the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0076] like Figure 2 As shown, by using the ranking scores finally obtained by the above algorithm, the payment collection devices are recalled and the delivery devices are selected. All the devices in the second set of devices can be directly used as delivery devices, or in the second set of devices, based on relevant business policies (such as blacklist and whitelist policies, user experience policies, offline content delivery upper limit policies, etc.), business policy refinement is performed again to select some payment collection devices as delivery devices. Of course, the business policy refinement can also be performed during the previous steps, for example, before the process of generating the first set of devices or the second set of devices.

[0077] based on Figure 1 This specification also provides some specific implementation plans and extension plans of the method, which will be described below.

[0078] In one or more embodiments of this specification, considering that the order of magnitude of offline merchant IoT devices (in order to ensure that both the first merchant and the second merchant can be analyzed, the merchant IoT devices considered here include the delivery terminal and the payment collection device) may reach a larger scale (for example, reaching millions, tens of millions or even higher) with the development of computer and network technology. Therefore, constructing a corresponding hash table (Hashtable, also known as a hash table) in advance based on the merchant IoT device set can ensure the response time of the algorithm and the user experience.

[0079] The actual geographical range is divided into regions in advance through relevant algorithms (for example, geohash algorithms), and the regional code hash values ​​corresponding to each region are obtained, and the merchant IoT device and the regional code hash value to which it belongs are established in correspondence. In this way, after determining the location of the merchant IoT device where the delivery end is located, the regional code hash value to which it belongs can be determined, which is used as the current hash value, and several surrounding regional code hash values ​​(for example, the regional code hash values ​​corresponding to the 8 regions adjacent to the region corresponding to the current hash value) are determined according to the current hash value, and are used as the surrounding hash values. In this way, multiple payment devices that can receive orders can be selected in the areas corresponding to the current hash value and the surrounding hash values ​​to form the first set of devices. Among them, when the regional code hash value is a 5-digit geohash, the actual geographical range corresponding to it is approximately 4 kilometers * 5 kilometers, which can meet the accuracy requirements of most algorithms and ensure a certain retrieval speed. Of course, the regional code hash value can also be set to a higher number of digits based on actual needs to improve the accuracy in the regional division process.

[0080] In one or more embodiments of this specification, it has been mentioned above that the relationship type may include a positive correlation type, a negative correlation type, etc. Here, from each of the fine-screening dimensions, a corresponding dimension set is generated according to the relationship type, and a differentiated dimension effect prediction scheme is determined according to the dimension set. For example, a part of the fine-screening dimensions that are negatively correlated with the delivery effect are used as a negative correlation dimension set; a part of the fine-screening dimensions that are positively correlated with the delivery effect are used as a positive correlation dimension set.

[0081] Specifically, as for the dimension of distance, as mentioned above, first, merchants often hope that the payment device can be as close to the delivery end as possible. Therefore, as the distance increases, the delivery effect decreases, and the dimension of distance belongs to the set of negatively correlated dimensions.

[0082] For the dimension of the number of cross-customers between the first merchant and the second merchant (a cross-customer refers to a user who is a customer of both the first merchant and the second merchant, and whether the user is a customer can be determined by whether the user has registered with the merchant, consumed goods, etc.), if the user is a customer of the first merchant, then after seeing the offline content delivered by the first merchant from the payment device of the second merchant, he is more motivated to go to the first merchant than other users. Therefore, as the number of cross-customers increases, the delivery effect increases, and the dimension of the number of cross-customers belongs to the set of positively correlated dimensions.

[0083] Of course, the number of cross-customers can be further divided into male cross-customers and female cross-customers according to user type (for example, user type division according to user gender). If the first merchant is a women's clothing store, and a male user has previously accompanied a female user to the first merchant to make purchases, becoming a cross-customer of the first merchant and the second merchant, then even if the male cross-customer sees the offline content delivered by the first merchant on the delivery device, the probability of actively going to the first merchant again is very small. At this point, the increase in the number of male cross-customers will actually have almost no effect on the delivery effect, while the increase in the number of female cross-customers will usually increase the delivery effect. The dimension of the number of cross-customers under a specific first merchant belongs to a discrete dimension set.

[0084] As for the dimension of time, in the course of business operations of some businesses, the periodic changes over time (for example, different time periods within a day, working days and non-working days within a week, different seasons within a year, etc.) will have a periodic impact on customers. For example, for restaurants, the customer flow is usually the highest during the three time periods corresponding to breakfast, lunch, and dinner within a day; for ice cream shops, the customer flow is the highest in the summer, followed by spring and autumn, and the least in winter. The increase or decrease in customer flow is positively correlated with the effect of delivery. Therefore, as time changes, the delivery effect changes periodically, and the dimension of time belongs to the set of periodic dimensions.

[0085] For the dimensions of a specific delivery activity, for example, the first merchant held a delivery activity related to offline content delivery, and clearly stated in the offline content delivered that when the number of viewers of the offline content reached a first number, the prizes of the first stage would be issued, and when the number of participants reached a second number (the second number was greater than the first number), the prizes of the second stage would be issued (the value of the prizes of the second stage was higher than the prizes of the first stage). At this time, when the number of viewers did not reach the first number, the delivery effect would increase with the increase in the number of viewers, but when the number of viewers reached the first number, the delivery effect would increase suddenly due to the existence of the prizes of the first stage, and the motivation of users to go to the first merchant after seeing the offline content delivered would increase suddenly, which would bring about a sudden increase in the delivery effect. Similarly, when the number of viewers reached the second number, the delivery effect would also increase suddenly. Therefore, with the increase in the number of viewers (or other factors), the delivery effect changes suddenly, and the dimensions of a specific delivery activity belong to the set of sudden dimensions.

[0086] Furthermore, the positive correlation dimension set and the negative correlation dimension set are more universal, and these two dimension sets are further explained here.

[0087] First, a selection function is determined according to the fine screening dimension to select the value corresponding to the fine screening dimension. When the selection function is not empty for the value of the fine screening dimension, a variable value determined according to the value of the fine screening dimension is returned (the variable value can be the value itself, or a value obtained according to the value and a preset coefficient). When the value of the fine screening dimension is empty, a settable threshold value is returned (the threshold value is used to replace the variable value).

[0088] A nonlinear transformation function is generated based on the selection function, and the nonlinear transformation function is used to normalize the values ​​of the fine screening dimensions, so as to facilitate the subsequent comprehensive processing of the delivery effects of multiple fine screening dimensions. Through the differentiated setting of threshold values ​​(the threshold value can be set to a particularly large or small value according to the positive correlation type and the negative correlation type, to replace the value of the fine screening dimension that does not exist) and the corresponding transformation of the proportional properties of the nonlinear transformation function (for example, according to the positive and negative correlation types, the positions of the numerator and denominator in the fraction are exchanged), differentiated dimension effect prediction schemes are determined for the positive correlation dimension set and the negative correlation dimension set.

[0089] For example, let the selection function be NVL(E 1 , E 2 ), where E 1 The variable value determined by the fine screening dimension, E 2 is the threshold value set. When the fine screening dimension belongs to the positive correlation dimension set, E 2 =0, when the fine screening dimension belongs to the negative correlation dimension set, E 2 =10 9 .

[0090] The nonlinear transformation function is expressed as When the fine screening dimension belongs to the set of positively correlated dimensions, the value of the fine screening dimension When the fine screening dimension belongs to the negatively correlated dimension set, the value of the fine screening dimension Among them, v i is the value of the i-th fine screening dimension, i is a natural number, determined based on the total number of fine screening dimensions, x i is the variable value determined by the value of the i-th fine screening dimension, and C is a constant. For the nonlinear transformation function sigmoid(x), its value range is (0, 1), so v i The value range is (-0.5, 0.5). Finally, the ranking scores of the cash collection equipment under all fine screening dimensions can be obtained. And∑ i λ i =1and k∈S 1 ; Among them, score k is the ranking score of the kth cash collection device under all fine screening dimensions, k is a natural number determined based on the total number of the first cash collection device, λ i is the weight corresponding to the i-th fine screening dimension, S 1 The first set for the device.

[0091] In one or more embodiments of this specification, when a user makes offline purchases in real life, there is a high probability that the user does not just go to one merchant to make purchases. For example, when a user is shopping in a shopping mall, he or she comes across a beverage store, a snack bar, and a clothing store that he or she is interested in, and makes purchases at each of them.

[0092] Based on this, the probability of customer service continuation between each first payment device is predicted according to the pre-generated merchant-related data set. The probability of customer service continuation refers to the probability that a user will continue to perform business at the next merchant after performing business (e.g., paying business fees, purchasing goods, purchasing services, etc.) at one merchant. Here, the probability of customer service continuation is determined by the first payment device corresponding to the merchant.

[0093] According to the probability of business continuation, multiple first payment devices (usually multiple first payment devices with the highest probability of business continuation for customers) are selected as continuation devices, and one or more continuation device chains are generated according to the continuation order between the continuation devices. The continuation device chain is generated based on the corresponding continuation devices in the prediction of the user's next behavior through data analysis, and can be regarded as an imaginary consumption chain in scenes such as shopping malls and shopping streets.

[0094] According to the attributes of each first payment device in the continuous device chain and the coordination between them, the cooperation effect score corresponding to the continuous device chain is obtained, and based on multiple fine-screening dimension scores of the first payment device in the continuous device chain and the cooperation effect score, a ranking score is generated for each first payment device.

[0095] Specifically, the probability of customer business continuation can be determined based on multiple factors such as business relevance, location relationship, and user habits between merchants. Merchants usually have certain business relevance. For example, if a user consumes in a KTV, he or she may feel thirsty and want to drink water or beverages after coming out. At this time, the probability that the next merchant he or she goes to is a beverage store or a convenience store (for the convenience of description, the following explanation is based on the beverage store as an example) will be very high. The business relevance between beverage stores and KTVs is relatively strong. According to the location relationship, the beverage stores that exist nearby are determined, and based on the user's historical consumption behavior, the user's preferences are determined (for example, the user has consumed beverage store A many times in the past, indicating his or her love for beverage store A). The probability of customer business continuation corresponding to the surrounding merchants (at least including beverage stores, and similar methods can also be used to judge other types of merchants nearby) can be obtained.

[0096] After selecting the first cashier device corresponding to Beverage Shop A based on the business connection probability, a similar analysis is performed to determine that the user is likely to continue to go to Snack Shop B. In this way, a connection device chain can be generated based on the connection sequence: KTV-Beverage Shop A-Snack Shop B, where the first cashier devices of Beverage Shop A and Snack Shop B are the connection devices. Of course, other connection device chains can also be generated in a similar manner.

[0097] The higher the service continuity probability between the continuous devices, the higher the service continuity probability, the higher the probability that the user will go to the next continuous device, and the higher the cooperation effect score. However, as the length of the continuous device chain increases, the overall prediction accuracy will also decrease. Therefore, for a longer continuous device chain, its cooperation effect score can be appropriately reduced.

[0098] In the process of calculating the ranking score, the fine screening dimension score is still used as the basic parameter, and the cooperation effect score is used as the coefficient to finally obtain the ranking score. The ranking score obtained in this way not only takes into account the fine screening dimensions of the first payment device under a single dimension, but also takes into account the cooperation between multiple first payment devices, so that the final result is closer to real life, which makes the ranking score more accurate.

[0099] Furthermore, the above has described how to generate a chain of subsequent devices. If the user follows the chain of subsequent devices, the user is likely to repeatedly see the offline content placed by the first merchant in the subsequent device. At this time, for some users, it may even have the opposite effect of making them bored.

[0100] Based on this, if it is determined that there is a continuous device chain in the second set, the offline content corresponding to the delivery request form is divided into multiple content segments. For example, if there are some continuous devices in a certain continuous device chain (these parts of the continuous devices are preferably continuous devices in the continuous device chain, so that better effects can be achieved. Of course, even if they are not continuous devices, they can also achieve certain effects), the video corresponding to the offline content is divided into multiple video segments in chronological order.

[0101] According to the order of the connecting devices in the connecting device chain, multiple content segments are matched, for example, one-to-one matching or one connecting device matching multiple content segments, to obtain matching results, and the content segments are delivered on the delivery device according to the matching results. In this way, when the user moves forward along the connecting device chain, he no longer sees repetitive offline content, but rather segments similar to a TV series, which can increase the user's interest in continuing to watch, and thus increase the user's attention to the offline content itself, thereby achieving a better delivery effect.

[0102] In one or more embodiments of this specification, it has been described above that the second set of devices can be further sorted by business strategy to select more suitable delivery devices. For the convenience of description, some or all of the payment collection devices in the second set of devices are referred to as second payment collection devices.

[0103] Specifically, the opening date of the second merchant where the second payment device is located is first determined, and whether the second merchant is a new store is determined based on the opening date and the current date (for example, a merchant whose time difference between the two is less than a preset threshold is defined as a new store). If it is a new store, the new store can be preferentially selected in the second set of devices according to the pre-set new store support strategy to increase the enthusiasm of the newly added second merchant.

[0104] Further, after it is determined to be a new store, the business scope corresponding to the second cash collection device is further determined, and each second cash collection device can correspond to one or more business scopes. The business scope may include catering scope, clothing scope, entertainment scope, etc., and of course it can be further divided, such as further dividing the catering scope into Chinese restaurants, Western restaurants, buffet restaurants, beverage shops, etc. According to the business scope and the business scope of other cash collection devices in the second set, the business intersection scope of the second cash collection device and other cash collection devices can be obtained. As the business intersection scope decreases, it means that the particularity of the second cash collection device in the second set of devices increases, and its irreplaceability in the second set of devices also increases accordingly. Even when the business intersection scope is 0, if there is a user who has a demand for the business scope of the second cash collection device, he can only go to the second set of the device (of course, he can also go to the cash collection device that is not in the second set of devices, but because it has been analyzed by the previous fine screening dimension, it is no longer within our consideration). Therefore, as the business intersection scope decreases, the probability of the second cash collection device being selected as the delivery device increases to ensure that offline content can be delivered to users with this part of the demand.

[0105] Based on the same idea, one or more embodiments of this specification also provide devices and apparatuses corresponding to the above methods, such as Figure 4 , Figure 5 shown.

[0106] Figure 4 A schematic diagram of the structure of an offline content delivery device based on a payment device provided for one or more embodiments of this specification, the device comprising:

[0107] The receiving module 402 receives a delivery request form sent by the delivery terminal of the first merchant;

[0108] A first screening module 404 is configured to screen payment collection devices of a plurality of second merchants that are located around the delivery end and can receive orders, to form a first set of devices;

[0109] The performance data determination module 406 determines a plurality of fine screening dimensions according to the pre-built merchant-related data set, and determines the performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0110] Prediction module 408, determining differentiated dimension effect prediction schemes according to the relationship type between each of the fine screening dimensions and the delivery effect, and predicting a plurality of fine screening dimension scores for each of the first payment collection devices based on the relationship type between each of the fine screening dimensions and the delivery effect, and combining the performance data with the scheme;

[0111] A ranking score determination module 410 determines the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0112] A second screening module 412, screening a portion of the first payment receiving devices according to the ranking scores to form a second set of devices;

[0113] The delivery module 414 determines a delivery device for the offline content of the delivery request in the second set of devices, and performs corresponding delivery.

[0114] Optionally, the first screening module 404 obtains a hash table constructed according to a preset merchant IoT device set;

[0115] Determine the region code hash value of the location of the merchant IoT device where the delivery end is located as the current hash value;

[0116] According to the current hash value, determine several surrounding area coded hash values ​​as surrounding hash values;

[0117] According to the current hash value and the surrounding hash values, multiple payment devices of the second merchant that can accept orders are indexed in the hash table to form a first set of devices.

[0118] Optionally, the region code hash value is a geohash with a number of digits not less than 5, and the plurality of region code hash values ​​are adjacent to the current hash value.

[0119] Optionally, the prediction module 408 determines, among the fine screening dimensions, a portion of the fine screening dimensions that are negatively correlated with the delivery effect as a negatively correlated dimension set, and determines a portion of the fine screening dimensions that are positively correlated with the delivery effect as a positively correlated dimension set;

[0120] Differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

[0121] Optionally, the prediction module 408 determines a selection function according to the fine screening dimension, and the selection function returns a variable value determined according to the value of the fine screening dimension when the value of the fine screening dimension is not empty, and returns a configurable threshold value when the value of the fine screening dimension is empty;

[0122] Determining a nonlinear transformation function according to the selection function, for normalizing the values ​​of the fine screening dimension;

[0123] By differentially setting the threshold value and correspondingly transforming the proportional property of the nonlinear transformation function, differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

[0124] Optionally, the negatively correlated dimension set includes at least: a dimension representing the distance between the merchant IoT device where the delivery end is located and the first payment receiving device;

[0125] The positive correlation dimension set includes at least: a dimension representing the number of cross-customers between the first merchant and the second merchant.

[0126] Optionally, the ranking score determination module 410 predicts the probability of customer business continuation between the first payment collection devices based on the merchant-related data set;

[0127] According to the customer service connection probability, select a plurality of first payment receiving devices from each of the first payment receiving devices as connection devices;

[0128] Determine a connection sequence between the connection devices to obtain one or more connection device chains, and determine a cooperation effect score of the connection device chains;

[0129] For the first cash collection device in the connecting device chain, the ranking score of the first cash collection device is determined according to the multiple fine screening dimension scores and the cooperation effect score of the first cash collection device.

[0130] Optionally, the delivery module 414 determines whether the second set of devices includes the connected device chain;

[0131] If yes, segment the offline content of the delivery request form to obtain multiple content segments;

[0132] Matching the order between the connecting devices in the connecting device chain with the order between the multiple content segments to obtain a sequence matching result;

[0133] The subsequent device in the subsequent device chain is determined as a delivery device, and the corresponding content segment is delivered on the corresponding delivery device according to the sequence matching result.

[0134] Optionally, the delivery module 414 determines a business opening date corresponding to a second payment collection device in the second set of devices;

[0135] Determining whether the second merchant corresponding to the second payment device is a new store according to the opening date and the current date;

[0136] If yes, then obtaining the business scope corresponding to the second payment device;

[0137] Determine the business overlap scope between the second payment receiving device and other payment receiving devices according to the business operation scope of the second payment receiving device and the business operation scope of other payment receiving devices in the second set of devices;

[0138] The delivery device is selected according to the business cross-range, and as the business cross-range decreases, the probability of the second payment collection device being selected as the delivery device increases.

[0139] Figure 5 A schematic diagram of the structure of an offline content delivery device based on a payment device provided for one or more embodiments of this specification, the device comprising:

[0140] at least one processor; and,

[0141] a memory communicatively connected to the at least one processor; wherein,

[0142] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0143] Receiving a delivery request form sent by the delivery terminal of the first merchant;

[0144] Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices;

[0145] Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0146] Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predict a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0147] Determine the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0148] According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices;

[0149] Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0150] Based on the same idea, one or more embodiments of this specification also provide a non-volatile computer storage medium corresponding to the above method, storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0151] Receiving a delivery request form sent by the delivery terminal of the first merchant;

[0152] Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices;

[0153] Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions;

[0154] Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and accordingly predict a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data;

[0155] Determine the ranking scores of the first payment receiving devices according to the multiple fine screening dimension scores of the first payment receiving devices;

[0156] According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices;

[0157] Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

[0158] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0159] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0160] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0161] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0162] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0163] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0164] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0165] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0166] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0167] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0168] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0169] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0170] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0171] Each embodiment in this specification 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 non-volatile computer 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.

[0172] The above is a description of a specific embodiment of the specification. 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.

[0173] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. An offline content delivery method based on a payment device, comprising: Receiving a delivery request form sent by the delivery terminal of the first merchant; Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices; Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions; Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and predict multiple fine screening dimension scores for each of the first payment collection devices based on the relationship type in combination with the performance data, wherein the relationship types include: positive correlation type, negative correlation type, periodicity type, mutation type, and discrete type; Determining the ranking scores of the first payment collection devices according to the multiple fine screening dimension scores of the first payment collection devices, specifically including: predicting the customer service continuation probability between the first payment collection devices according to the merchant-related data set, selecting multiple first payment collection devices from the first payment collection devices as continuation devices according to the customer service continuation probability, determining the continuation order between the continuation devices, obtaining one or more continuation device chains, and determining the cooperation effect score of the continuation device chain; for the first payment collection device in the continuation device chain, determining the ranking score of the first payment collection device according to the multiple fine screening dimension scores and the cooperation effect score of the first payment collection device, wherein the customer service continuation probability refers to the probability that a user, after performing a business in one merchant, will go to the next merchant to continue performing the business; According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices; Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

2. The method according to claim 1, wherein the step of screening multiple payment collection devices of second merchants that are located around the delivery end and can accept orders to form a first set of devices specifically comprises: Get the hash table constructed based on the preset merchant IoT device set; Determine the region code hash value of the location of the merchant IoT device where the delivery end is located as the current hash value; According to the current hash value, determine several surrounding area coded hash values ​​as surrounding hash values; According to the current hash value and the surrounding hash values, multiple payment devices of the second merchant that can accept orders are indexed in the hash table to form a first set of devices.

3. The method as claimed in claim 2, wherein the region code hash value is a geohash having a number of digits not less than 5, and the plurality of region code hash values ​​are adjacent to the current hash value.

4. The method according to claim 1, wherein determining a differentiated dimension effect prediction scheme according to the relationship type between each of the fine screening dimensions and the delivery effect specifically comprises: In each of the fine screening dimensions, a portion of the fine screening dimensions that are negatively correlated with the delivery effect is determined as a negatively correlated dimension set, and a portion of the fine screening dimensions that are positively correlated with the delivery effect is determined as a positively correlated dimension set; Differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

5. The method according to claim 4, wherein the step of determining differentiated dimension effect prediction schemes for the negatively correlated dimension set and the positively correlated dimension set comprises: Determine a selection function according to the fine screening dimension, wherein the selection function returns a variable value determined according to the value of the fine screening dimension when the value of the fine screening dimension is not empty, and returns a settable threshold value when the value of the fine screening dimension is empty; Determining a nonlinear transformation function according to the selection function, for normalizing the values ​​of the fine screening dimension; By differentially setting the threshold value and correspondingly transforming the proportional property of the nonlinear transformation function, differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

6. The method according to claim 4 or 5, wherein the negatively correlated dimension set at least includes: The dimension representing the distance between the merchant IoT device where the delivery end is located and the first payment receiving device; The positive correlation dimension set includes at least: a dimension representing the number of cross-customers between the first merchant and the second merchant.

7. The method according to claim 1, wherein determining the delivery device of the offline content of the delivery request in the second set of devices and performing corresponding delivery comprises: Determining whether the second set of devices includes the connecting device chain; If yes, segment the offline content of the delivery request form to obtain multiple content segments; Matching the order between the connecting devices in the connecting device chain with the order between the multiple content segments to obtain a sequence matching result; The subsequent device in the subsequent device chain is determined as a delivery device, and the corresponding content segment is delivered on the corresponding delivery device according to the sequence matching result.

8. The method according to claim 1, wherein determining the delivery device of the offline content of the delivery request in the second set of devices specifically comprises: Determine a business opening date corresponding to a second payment collection device in the second set of devices; Determining whether the second merchant corresponding to the second payment device is a new store according to the opening date and the current date; If yes, then obtaining the business scope corresponding to the second payment device; Determine the business overlap scope between the second payment receiving device and other payment receiving devices according to the business operation scope of the second payment receiving device and the business operation scope of other payment receiving devices in the second set of devices; The delivery device is selected according to the business cross-range, and as the business cross-range decreases, the probability of the second payment collection device being selected as the delivery device increases.

9. An offline content delivery device based on a payment device, comprising: A receiving module receives a delivery request form sent by a delivery terminal of the first merchant; A first screening module is configured to screen payment collection devices of a plurality of second merchants that are located around the delivery end and can receive orders, so as to form a first set of devices; a performance data determination module, which determines a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determines the performance data of each first payment collection device in the first set of devices on the fine screening dimensions; A prediction module determines a differentiated dimension effect prediction scheme according to the relationship type between each of the fine screening dimensions and the delivery effect, and predicts a plurality of fine screening dimension scores for each of the first payment collection devices based on the relationship type between each of the fine screening dimensions and the delivery effect, and predicts a plurality of fine screening dimension scores for each of the first payment collection devices in combination with the performance data, wherein the relationship types include: positive correlation type, negative correlation type, periodicity type, mutation type, and discrete type; The ranking score determination module determines the ranking scores of the first payment collection devices according to the multiple fine screening dimension scores of the first payment collection devices, specifically including: predicting the customer service continuation probability between the first payment collection devices according to the merchant-related data set, selecting multiple first payment collection devices from the first payment collection devices as continuation devices according to the customer service continuation probability, determining the continuation order between the continuation devices, obtaining one or more continuation device chains, and determining the cooperation effect score of the continuation device chain; for the first payment collection device in the continuation device chain, determining the ranking score of the first payment collection device according to the multiple fine screening dimension scores and the cooperation effect score of the first payment collection device, wherein the customer service continuation probability refers to the probability that a user, after performing a business in one merchant, will go to the next merchant to continue performing the business; A second screening module, screening a portion of the first payment receiving devices according to the ranking scores to form a second set of devices; The delivery module determines the delivery device of the offline content of the delivery request form in the second set of devices, and performs corresponding delivery.

10. The device according to claim 9, wherein the first screening module obtains a hash table constructed according to a preset merchant IoT device set; Determine the region code hash value of the location of the merchant IoT device where the delivery end is located as the current hash value; According to the current hash value, determine several surrounding area coded hash values ​​as surrounding hash values; According to the current hash value and the surrounding hash values, multiple payment devices of the second merchant that can accept orders are indexed in the hash table to form a first set of devices.

11. The apparatus as claimed in claim 10, wherein the region code hash value is a geohash having a number of digits not less than 5, and the plurality of region code hash values ​​are adjacent to the current hash value.

12. The device according to claim 9, wherein the prediction module determines, among the fine screening dimensions, a portion of the fine screening dimensions that are negatively correlated with the delivery effect as a negatively correlated dimension set, and determines a portion of the fine screening dimensions that are positively correlated with the delivery effect as a positively correlated dimension set; Differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

13. The device according to claim 12, wherein the prediction module determines a selection function according to a fine screening dimension, wherein the selection function returns a variable value determined according to the value of the fine screening dimension when the value of the fine screening dimension is not empty, and returns a configurable threshold value when the value of the fine screening dimension is empty; Determining a nonlinear transformation function according to the selection function, for normalizing the values ​​of the fine screening dimension; By differentially setting the threshold value and correspondingly transforming the proportional property of the nonlinear transformation function, differentiated dimensional effect prediction schemes are determined for the negatively correlated dimension set and the positively correlated dimension set.

14. The apparatus according to claim 12 or 13, wherein the negative correlation dimension set at least includes: The dimension representing the distance between the merchant IoT device where the delivery end is located and the first payment receiving device; The positive correlation dimension set includes at least: a dimension representing the number of cross-customers between the first merchant and the second merchant.

15. The apparatus according to claim 9, wherein the delivery module determines whether the second set of devices includes the connecting device chain; If yes, segment the offline content of the delivery request form to obtain multiple content segments; Matching the order between the connecting devices in the connecting device chain with the order between the multiple content segments to obtain a sequence matching result; The subsequent device in the subsequent device chain is determined as a delivery device, and the corresponding content segment is delivered on the corresponding delivery device according to the sequence matching result.

16. The apparatus of claim 9, wherein the delivery module determines a business opening date corresponding to a second payment collection device in the second set of devices; Determining whether the second merchant corresponding to the second payment device is a new store according to the opening date and the current date; If yes, then obtaining the business scope corresponding to the second payment device; Determine the business overlap scope between the second payment receiving device and other payment receiving devices according to the business operation scope of the second payment receiving device and the business operation scope of other payment receiving devices in the second set of devices; The delivery device is selected according to the business cross-range, and as the business cross-range decreases, the probability of the second payment collection device being selected as the delivery device increases.

17. An offline content delivery device based on a payment device, comprising: at least one processor; as well as, 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 enable the at least one processor to: Receiving a delivery request form sent by the delivery terminal of the first merchant; Filtering payment collection devices of a plurality of second merchants that are located around the delivery end and can accept orders to form a first set of devices; Determine a plurality of fine screening dimensions according to a pre-constructed merchant-related data set, and determine performance data of each first payment collection device in the first set of devices on the fine screening dimensions; Determine a differentiated dimension effect prediction scheme based on the relationship type between each of the fine screening dimensions and the delivery effect, and predict multiple fine screening dimension scores for each of the first payment collection devices based on the relationship type in combination with the performance data, wherein the relationship types include: positive correlation type, negative correlation type, periodicity type, mutation type, and discrete type; Determining the ranking scores of the first payment collection devices according to the multiple fine screening dimension scores of the first payment collection devices, specifically including: predicting the customer service continuation probability between the first payment collection devices according to the merchant-related data set, selecting multiple first payment collection devices from the first payment collection devices as continuation devices according to the customer service continuation probability, determining the continuation order between the continuation devices, obtaining one or more continuation device chains, and determining the cooperation effect score of the continuation device chain; for the first payment collection device in the continuation device chain, determining the ranking score of the first payment collection device according to the multiple fine screening dimension scores and the cooperation effect score of the first payment collection device, wherein the customer service continuation probability refers to the probability that a user, after performing a business in one merchant, will go to the next merchant to continue performing the business; According to the ranking scores, a portion of the first payment receiving devices are selected to form a second set of devices; Determine the delivery device of the offline content of the delivery request in the second set of devices, and perform corresponding delivery.

Images