CN113888219A

CN113888219A - Offline content delivery method, device and equipment based on cash collecting equipment

Info

Publication number: CN113888219A
Application number: CN202111176120.3A
Authority: CN
Inventors: 黄博
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2021-10-09
Filing date: 2021-10-09
Publication date: 2022-01-04

Abstract

The embodiment of the specification discloses an offline content delivery method, device and equipment based on a cash register. The scheme comprises the following steps: receiving a releasing request sheet sent by a releasing end of a first merchant; screening a plurality of second merchant money collecting devices which are positioned around the releasing end and can receive orders to form a first set of devices; determining a plurality of fine screening dimensions according to a pre-constructed merchant related data set, and determining the performance data of each first collection device in a first set of devices in the fine screening dimensions; according to the relationship type between each fine screening dimension and the putting effect, a differentiated dimension effect prediction scheme is determined, and a plurality of fine screening dimension scores are respectively predicted for each first collection device according to the difference and the performance data; determining the sorting score of each first money receiving device according to the fine screening dimension scores of each first money receiving device; screening a part of first collection equipment according to the sorting scores to form a second set of equipment; and determining the releasing devices of the offline content of the releasing request list in the second set of devices, and performing corresponding releasing.

Description

Offline content delivery method, device and equipment based on cash collecting equipment

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method, an apparatus, and a device for offline content delivery based on a cash register.

Background

With the development of computer and internet technologies, the content released by the merchants can be seen in more and more scenes.

In the traditional offline content delivery process, the delivery host and the device host have different information, and both sides need to find business opportunities by themselves and determine the future delivery effect by human experience. Moreover, the devices owned by the device owners are generally content delivery dedicated devices (such as advertisement machines, large-scale LED display screens, and the like), and the application scenes of the devices are often fixed, for example, the devices are applied to scenes such as subway stations, bus stations, office buildings, and the like, so that users do not pay special attention to the delivered content, and the delivery cost is high due to site rent, device maintenance, and the like.

Based on this, a scheme that can better ensure the offline content delivery effect is needed.

Disclosure of Invention

One or more embodiments of the present disclosure provide a method, an apparatus, a device, and a storage medium for offline content delivery based on a payment device, so as to solve the following technical problems: a scheme that can better ensure the offline content delivery effect is required.

To solve the above technical problem, one or more embodiments of the present specification are implemented as follows:

one or more embodiments of the present specification provide an offline content delivery method based on a payment receiving device, including:

receiving a releasing request sheet sent by a releasing end of a first merchant;

screening a plurality of second merchant money collecting devices which are positioned around the releasing end and can receive orders to form a first set of devices;

determining a plurality of fine screening dimensions according to a pre-constructed merchant related data set, and determining performance data of each first collection device in the first device set on the fine screening dimensions;

determining a differentiated dimensionality and effect prediction scheme according to the relationship type between the fine screening dimensionality and the putting effect, and predicting a plurality of fine screening dimensionality fractions for the first collection equipment respectively by combining the performance data;

determining the sorting score of each first money collecting device according to the fine screening dimension scores of each first money collecting device;

screening a part of the first money receiving equipment according to the sorting scores to form a second set of equipment;

and determining the releasing equipment of the offline content of the releasing request list in the second equipment set, and performing corresponding releasing.

One or more embodiments of the present specification provide an offline content delivery apparatus based on a payment receiving device, including:

the receiving module is used for receiving a releasing request sheet sent by a releasing end of a first merchant;

the first screening module screens the money receiving equipment of a plurality of second merchants which can receive orders and are positioned around the releasing end to form a first equipment set;

the performance data determining module is used for determining a plurality of fine screening dimensions according to a pre-constructed merchant related data set and determining performance data of each first payment device in the first device set on the fine screening dimensions;

the prediction module is used for determining a differentiated dimensionality effect prediction scheme according to the relationship type between each fine screening dimensionality and the putting effect, and predicting a plurality of fine screening dimensionality scores for each first collection device respectively by combining the performance data;

the sorting score determining module is used for determining the sorting score of each first money receiving device according to the fine screening dimension scores of each first money receiving device;

the second screening module screens a part of the first cash collecting equipment according to the sorting scores to form an equipment second set;

and the releasing module is used for determining releasing equipment of the offline content of the releasing request list in the second equipment set and performing corresponding releasing.

One or more embodiments of the present specification provide an offline content delivery device based on a payment receiving device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to:

One or more embodiments of the present specification provide a non-transitory computer storage medium storing computer-executable instructions configured to:

At least one technical scheme adopted by one or more embodiments of the specification can achieve the following beneficial effects:

compared with a special releasing device, the application scene of the payment receiving device is wider, and the attention degree brought by the payment receiving device is higher for a user who needs to execute a payment service, so that a better releasing effect can be brought to a first merchant. The cash collecting equipment is usually small in size and can be used after being installed in stores of all merchants, the site cost is saved, meanwhile, special maintenance is not needed, the cost required by the first merchant when the content of the first merchant is released is reduced, the second merchant can increase the self income through releasing the content of the second merchant, the effect of diversified utilization of the cash collecting equipment is achieved, and the win-win situation of both parties is realized.

By setting a plurality of fine screening dimensions and adopting a differentiated dimension effect prediction scheme for different collection devices, the sorting fraction of each collection device is obtained through prediction, the most appropriate collection device is selected for the releasing end according to the sorting fraction obtained through prediction, the final releasing effect is guaranteed, and the benefit of a releasing owner and a device owner is also guaranteed.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without any creative effort.

Fig. 1 is a schematic flow chart of an offline content delivery method based on a payment receiving device according to one or more embodiments of the present disclosure;

fig. 2 is a schematic block diagram of an offline content delivery system based on a payment receiving device according to one or more embodiments of the present disclosure;

fig. 3 is a schematic process diagram of a recall of a checkout device in an offline content delivery method based on a checkout device according to one or more embodiments of the present disclosure;

fig. 4 is a schematic structural diagram of an offline content delivery apparatus based on a payment receiving device according to one or more embodiments of the present disclosure;

fig. 5 is a schematic structural diagram of an offline content delivery device based on a checkout device according to one or more embodiments of the present disclosure.

Detailed Description

The embodiment of the specification provides an offline content delivery method, an offline content delivery device, offline content delivery equipment and a storage medium based on a cash register.

In order to make those skilled in the art better understand the technical solutions in the present specification, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any inventive step based on the embodiments of the present disclosure, shall fall within the scope of protection of the present application.

Fig. 1 is a flowchart illustrating a method for offline content delivery based on a payment receiving device at a server side according to one or more embodiments of the present disclosure. The method can be applied to different business fields, such as the offline payment field, the internet financial business field, the electric business field, the instant messaging business field, the game business field, the official business field and the like. The process may be performed by computing devices in the corresponding domain (e.g., a server, a cash register, etc. corresponding to the offline payment service), and some input parameters or intermediate results in the process allow for manual intervention and adjustment to help improve accuracy.

The process in fig. 1 may include the following steps:

s102: and receiving a releasing request sheet sent by a releasing end of a first merchant.

Figure 2 is a block diagram of a system for offline content delivery based on a checkout device according to one or more embodiments of the present disclosure, when a merchant has a content delivery requirement (hereinafter, the merchant is referred to as a first merchant or a delivery host), the first merchant sends a delivery request sheet to a server through a corresponding device (herein, the device is referred to as a delivery end), the delivery request sheet carries the delivery requirement of the first merchant, the release demand directly or indirectly expresses the offline content that the first merchant wants to release at this time and the selected release package (including the number of release days, the number of release devices, and the like), for example, the release demand may be a video, a poster, or an audio that can be directly used for releasing the offline content, or may be a textual description reflecting the requirement of the first merchant, and the content that can be used for being directly released is made by the server or the third party according to the textual description. The releasing end can be a mobile phone, a Personal Computer (PC), a money receiving device and other terminal devices with corresponding functions.

S104: and screening a plurality of second merchant money collecting devices which are positioned around the releasing end and can receive orders to form a first set of devices.

Types of the receiving device include various types, which can perform a receiving transaction based on a two-dimensional code, a credit card, etc., for example, a user completes a payment by displaying a payment code of the user to the receiving device, scanning the receiving code displayed by the receiving device, swiping a card on the receiving device, etc., and a merchant who owns the receiving device is referred to as a second merchant or a device owner.

If the release request is received, the final release effect is not good easily by the traditional release mode and depending on manual experience or indiscriminate selection of the cash collecting device, and the benefit of the release owner and the device owner is affected. For offline content delivery, a first merchant usually pays attention to the location of the payment receiving device, and the payment receiving device is expected to be close to a store of the first merchant, so that a potential user can quickly reach the store of the first merchant when the payment receiving device sees the delivered offline content. Even when the first merchant is close enough to the payment device, the user can see the store of the first merchant as soon as the user lifts his head while seeing the released offline content from the payment device, and at this time, the user can reach the first merchant only by a short number of steps, and if the user is interested in the released offline content, the user has a very high probability of going to the first merchant.

Based on this, the location of the first merchant store is determined by the location information of the drop terminal, but since the drop terminal may be a mobile device, the location information may change due to the movement of the drop master, and thus the location information of the drop terminal may not be determined by the terminal, but may be specified by the drop master. Whether the collection device is located around the drop end is determined according to the position information of the drop end and the collection devices (whether the collection device is located around can be determined based on a preset distance, for example, the around can refer to the collection device within 2 kilometers of the radius of the drop end). For example, the distance between the dispensing end and each of the money collecting devices is determined by Location Based Services (LBS) coordinates of the dispensing end and the money collecting devices, and then whether the money collecting devices are located around the dispensing end is determined.

Of course, in order to ensure the experience of the second merchant, in the process of constructing the first set of devices, the selection of the payment device is only performed in the second merchant who can receive the order. Whether the order accepting state is available or not is selected by the second merchant, and the second merchant can change the order accepting state based on the requirement and actual situation of the second merchant. At the moment, the first merchant and the second merchant both express the desire of off-line content delivery, the server plays a role of matching more, and the first merchant and the second merchant are matched together to realize the win-win of both parties.

S106: according to a pre-constructed merchant related data set, a plurality of fine screening dimensions are determined, and performance data of each first collection device in the first collection of devices on the fine screening dimensions are determined.

The merchant related data set includes related data corresponding to the first merchant and the second merchant, and the related data may include merchant information (e.g., location information, dispensing end information, payment device information, etc.), transaction information (e.g., transaction service field, transaction amount, etc.), historical offline content dispensing information, etc., and may be stored in the form of a knowledge graph.

Fig. 3 is a schematic diagram of a process of cashing back a cashing device in an offline content delivery method based on a cashing device according to one or more embodiments of the present specification, and in fig. 3, 3 fine screening dimensions are taken as an example, where the fine screening dimensions refer to preset dimensions for screening the cashing devices, and performance data can embody relevant performances of the cashing devices in the first set of devices (for convenience of description, the cashing devices in the first set of devices are referred to as first cashing devices) in the fine screening dimensions. The performance data is based on different fine screening dimensions, and has a plurality of embodiments, for example, for the dimension of the distance, the distance between the collection device and the region to which the delivery end belongs can be used as the performance data, and for the dimension of the transaction amount, the transaction amount or the transaction amount of the collection device in a corresponding time period can be used as the performance data.

S108: and determining a differentiated dimensionality and effect prediction scheme according to the relationship type between each fine screening dimensionality and the putting effect, and predicting a plurality of fine screening dimensionality fractions for each first collection device respectively by combining the performance data.

The releasing effect refers to a positive effect brought to the releasing end, and may include economic benefits brought to the releasing end, user attention, access amount, topic amount and the like, and it may be determined which releasing effects the first merchant pays more attention to based on the releasing demand in the releasing request sheet, so as to perform more targeted screening on the payment receiving device. The release effect is not an actual release effect generated after the offline content is released, and mainly refers to an estimated release effect of the offline content by combining the performance data of the first payment receiving device through manual experience, historical data analysis, a related algorithm and the like.

The relationship type includes a plurality of types, such as a positive correlation type (the delivery effect increases with the increase of the performance data), a negative correlation type (the delivery effect decreases with the increase of the performance data), a periodic type (the delivery effect changes periodically with the continuous change of the performance data), a mutation type (the delivery effect keeps changing suddenly with the continuous change of the performance data), a discrete type (only partial change of the performance data can affect the delivery effect), and the like. Of course, the relationship type may be further divided to obtain a more accurate relationship type, for example, the positive correlation type is further divided into a linear positive correlation type, a non-linear positive correlation type, and the like.

The differential dimension effect prediction scheme refers to a prediction scheme under a corresponding dimension obtained by performing differential setting according to different relation types, and the prediction scheme comprises prediction through modes such as a pre-trained model, a pre-set formula and human experience.

As shown in fig. 3, the fine screening dimension score is obtained by taking the performance data as input under the fine screening dimension, analyzing and predicting the input performance data through the corresponding differentiated dimension effect prediction scheme, and then outputting the input performance data. The fine screening dimension fraction can embody the influence degree of the cash collecting device on the putting effect under the fine screening dimension, and generally speaking, the higher the fine screening dimension fraction is, the better the putting effect can be achieved by the cash collecting device.

S110: and determining the sorting score of each first money collecting device according to the fine screening dimension scores of each first money collecting device.

As shown in fig. 3, for each first money receiving device, a plurality of fine screen dimensions are provided, and naturally, a plurality of fine screen dimension fractions can be obtained. And after comprehensively processing the plurality of fine screening dimension fractions, sequencing according to the grades to obtain sequencing fractions. The fine screen dimension scores can only reflect the putting effect that the collection equipment can play under a single fine screen dimension, and the sorting scores can reflect a more complete putting effect that the collection equipment can play under all fine screen dimensions.

Specifically, the integration process may adopt various manners, for example, the ranking score is obtained by weighting according to the preset weight of each fine screening dimension and the corresponding fine screening dimension score. Or selecting part of fine screening dimensions to obtain a sorting score according to the throwing requirements in the throwing request list.

S112: and screening a part of the first money receiving devices according to the sorting scores to form a second set of devices.

In the screening process of the first cash collecting devices, a part of the first cash collecting devices with the highest ranking scores are usually selected to form a second set of devices, so that the best putting effect can be brought to the first merchant. However, in some special cases, for example, the reason of the delivery end itself (the selected package is a low-level package, and there is a fear that the goods are difficult to supply due to too much traffic), the reason of the first payment device side (the offline content delivery of several first payment devices with the highest ranking score is saturated), and the like, a part of the first payment devices with the highest ranking score not forming the second set of devices is selected, but the first payment devices with the highest ranking score are still selected to ensure the benefit of the first merchant.

S114: and determining the releasing equipment of the offline content of the releasing request list in the second equipment set, and performing corresponding releasing.

As shown in fig. 2, the collection devices are recalled and the releasing devices are selected according to the ranking scores finally obtained by the above algorithm, all devices in the second set of devices may be directly used as releasing devices, or based on relevant business policies (for example, a black-and-white list policy, a user experience policy, an offline content releasing upper limit policy, and the like), another business policy is refined and part of the collection devices are selected as releasing devices in the second set of devices. Of course, the business policy refinement may 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.

Based on the process of fig. 1, some specific embodiments and embodiments of the process are also provided in the present specification, and the description is continued below.

In one or more embodiments of the present disclosure, the magnitude of the 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 herein include a drop terminal and a cash receiving device) may reach a larger scale (e.g., reach millions, tens of millions, or even higher) with the development of computer and network technologies. Therefore, a corresponding hash table (Hashtable, also called as hash table) is constructed in advance according to the merchant IoT device set, so that the response time of the algorithm can be ensured, and the user experience is ensured.

The actual geographic range is divided into regions by a related algorithm (e.g., a geo-hash (geohash) algorithm) in advance to obtain region-coded hash values corresponding to the regions, and a corresponding relationship is established between the merchant IoT device and the region-coded hash value to which the merchant IoT device belongs. After the position of the merchant IoT device where the releasing end is located is determined, the area code hash value to which the releasing end belongs can be determined, the area code hash value is used as a current hash value, and a plurality of surrounding area code hash values (for example, area code hash values corresponding to 8 adjacent areas corresponding to the area corresponding to the current hash value) are determined according to the current hash value, and are used as surrounding hash values. Therefore, a plurality of money receiving devices which can receive orders can be selected in the area corresponding to the current hash value and the surrounding hash values to form a first set of devices. When the hash value of the regional code is a 5-bit geohash, the corresponding actual geographic range is about 4 km by 5 km, so that the accuracy requirement of most algorithms can be met, and a certain retrieval speed is ensured. Of course, the region encoding hash value may also be set to a higher number of bits based on actual requirements, so as to improve the precision in the region dividing process.

In one or more embodiments of the present description, it has been mentioned above that relationship types may include positive correlation types, negative correlation types, and the like. And generating a corresponding dimension set according to the relationship type from each fine screening dimension, and determining a differentiated dimension effect prediction scheme according to the dimension set. For example, a part of fine screening dimensions which are negative correlation relationship types between the fine screening dimensions and the putting effect are used as a negative correlation dimension set; and taking a part of fine screening dimensions which are in positive correlation with the putting effect as a positive correlation dimension set.

In particular, with respect to the dimension of distance, it has been mentioned above that the first merchant often desires the checkout device to be as close as possible to the dispensing end. Therefore, as the distance increases, the launch effect decreases, and the dimension of the distance belongs to the set of negative correlation dimensions.

For the dimension of the number of cross-customers between the first merchant and the second merchant (cross-customers means that the user is a customer of both the first merchant and the second merchant, whether the user is a customer can be determined by whether the user is registered at the merchant, consumed, etc.), if the user is a customer of the first merchant, the user is more motivated to go to the first merchant than other users after seeing the offline content released by the first merchant from the payment device of the second merchant. Therefore, as the number of cross clients increases, the delivery effect increases, and the dimension of the number of cross clients is the positive correlation dimension set.

Of course, the number of cross clients may be further divided into the number of male cross clients and the number of female cross clients according to the user type (for example, the user type is divided according to the gender of the user). If the first merchant is a woman shop and a male user is previously accompanied by a female user and is consumed when the female user goes to the first merchant, the male user becomes a cross-client of the first merchant and the second merchant, and even if the male cross-client sees the offline content released by the first merchant in the releasing equipment, the probability of actively going to the first merchant again is very small. At this time, the increase of the number of male cross-clients has practically no influence on the delivery effect, while the increase of the number of female cross-clients generally causes the delivery effect to increase, and the dimension of the number of cross-clients under a specific first merchant belongs to the discrete dimension set.

With respect to the time dimension, it may have a periodic effect on customers over time during business processes of some businesses (e.g., different time periods during a day, weekdays and non-weekdays during a week, different seasons of a year, etc.). For example, for a restaurant, the customer traffic is typically highest during three time periods corresponding to breakfast, lunch, and dinner during a day; for ice cream shops, the flow of customers is highest in summer and lowest in winter within one year, and the flow of customers is next to spring and autumn. And the increase and decrease of the customer flow and the delivery effect are in positive correlation. Therefore, the release effect generates periodic variation along with the variation of time, and the dimension of time belongs to the periodic dimension set.

For a particular dimension of the delivery event, for example, a first merchant has held a delivery event associated with the delivery of offline content, and explicitly shows in the delivered offline content that a first stage of prizes are awarded when the number of viewers of the offline content reaches a first number, and a second stage of prizes (the second stage of prizes having a higher value than the first stage of prizes) are awarded when the number of participants reaches a second number (the second number being greater than the first number). At this time, when the number of viewers does not reach the first number, the releasing effect is increased along with the increase of the number of viewers, but when the number of viewers reaches the first number, the releasing effect is improved due to the existence of the prize in the first stage, and after the user sees the released offline content, the motivation of the user to the first merchant is increased, and the releasing effect is increased abruptly. Similarly, the impression effect will also produce an increase in catastrophe nature when the number of viewers reaches a second number. Thus, as the number of viewers (or other factors) increases, the impression effect produces a change in the nature of the mutation, the dimensions of a particular impression campaign belonging to the set of mutated dimensions.

Further, the generality of the positive correlation dimension set and the negative correlation dimension set is strong, and the two dimension sets are further explained here.

Firstly, a selection function is determined according to the fine screening dimension and is used for selecting a value corresponding to the fine screening dimension. When the value of the selection function for the fine screening dimension is not null, 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), and when the value of the fine screening dimension is null, a settable threshold value (the threshold value is used for replacing the variable value) is returned.

And generating a nonlinear transformation function according to the selection function, wherein the nonlinear transformation function is used for carrying out normalization processing on the values of the fine screening dimensions so as to carry out comprehensive processing on the subsequent throwing effects of a plurality of fine screening dimensions. Through the differentiation setting of the threshold value (the threshold value can be set to be a particularly large or small value according to the difference of the positive correlation type and the negative correlation type to replace the value under the nonexistent fine screening dimension) and the proportional property transformation of the corresponding pair of nonlinear transformation functions (for example, according to the positive correlation type and the negative correlation type, the positions of a numerator and a denominator in a fraction are exchanged), a differentiated dimension effect prediction scheme is determined for the positive correlation dimension set and the negative correlation dimension set.

For example, the selection function is denoted as NVL (E)₁，E₂) Wherein E is₁Variable values determined for the values of the fine screening dimensions, E₂Is a set threshold value. When the fine screening dimension belongs to the positive correlation dimension set, E₂0, when the fine screen dimension belongs to the set of negative correlation dimensions, E₂＝10⁹。

Let the non-linear transformation function be

Value of fine screening dimension when the fine screening dimension belongs to positive correlation dimension set

When the fine screening dimension belongs to the negative correlation dimension set, the value of the fine screening dimension

Wherein v is_iIs the value of the ith fine screening dimension, i is a natural number, and x is determined based on the total number of the fine screening dimensions_iAnd C is a constant. For the nonlinear transformation function sigmoid (x), the value range is (0, 1), and therefore v_iThe value range of (1) is (-0.5, 0.5). Finally, the sorting fraction of the cash register under all fine screening dimensions can be obtained

And sigma_iλ_i＝1and k∈S₁(ii) a Wherein, score_kThe sorting fraction of the kth collection device under all fine screening dimensions, k is a natural number and is determined based on the total number of the first collection device, lambda_iFor the weight corresponding to the ith fine screen dimension, S₁Is a first set of devices.

In one or more embodiments of the present disclosure, when a user performs offline consumption in real life, there is a high probability that the user does not go to only one merchant for consumption. For example, during shopping at a mall, a user encounters a beverage store, a snack store, and a clothing store of interest, and goes to the respective stores for consumption.

Based on the above, the customer service connection probability among the first cash collecting devices is predicted according to the pre-generated related data set of the commercial tenant. The customer service connection probability refers to a probability that a user continues to execute a service to a next merchant after executing the service (for example, service payment, commodity purchase, service purchase, and the like) in one merchant, where the customer service connection probability is determined through a first payment receiving device corresponding to the merchant.

According to the service connection probability, a plurality of first collection devices (usually, a plurality of first collection devices with the highest customer service connection probability) are selected as connection devices, and one or more connection device chains are generated according to the connection sequence among the connection devices. The following behavior of the user is predicted through data analysis, and then the following behavior is generated according to the corresponding following equipment in the prediction, and the following equipment chain can be regarded as a virtual consumption chain in scenes such as shopping malls, shopping malls and the like.

And obtaining a cooperation effect score corresponding to the continuous equipment chain according to the attribute of each first collection equipment in the continuous equipment chain and the cooperation between the first collection equipment and the continuous equipment chain, and generating a sequencing score for each first collection equipment based on a plurality of fine screening dimension scores of the first collection equipment in the continuous equipment chain and the cooperation effect score.

Specifically, the customer service connection probability may be determined based on multiple factors such as service relevance between merchants, location relationship, user habits, and the like. There is usually a certain business relevance between merchants, for example, after a user consumes a KTV, the user is likely to feel thirsty and want to drink water or drink, and at this time, the probability that the user goes to the next merchant as a beverage shop or a convenience store (for convenience of description, the following explanation is given by taking a beverage shop as an example) is high, and the business relevance between the beverage shop and the KTV is strong. According to the position relationship, the beverage stores existing nearby are determined, and the preference of the user is determined based on the historical consumption behavior of the user (for example, the user historically consumes the beverage store a for multiple times and shows the preference of the beverage store a), so that the customer service continuation probability corresponding to each merchant around the time (at least including the beverage store, and other types of merchants nearby can also be judged by adopting a similar method) can be obtained.

And after the first payment receiving equipment corresponding to the drink shop A is selected according to the business continuation probability, analyzing in a similar mode, and considering that the user is likely to go to the snack shop B next. Thus, a connection device chain can be generated according to the connection sequence: the KTV-A beverage shop-B snack shop, wherein the first payment devices of the A beverage shop and the B snack shop are the connecting devices. Of course, other chains of successive devices may continue to be generated in a similar manner.

The higher the service connection probability between the cooperation effect score and each continuous device is, the higher the service connection probability is, and the higher the probability of the user going to the next continuous device is, the higher the cooperation effect score is. However, as the length of the persistence device chain increases, the overall prediction accuracy also decreases, and therefore, for a longer persistence device chain, the cooperative effect score may be appropriately reduced.

In the process of calculating the sorting score, the fine screening dimension score is still used as a basic parameter, the cooperation effect score is used as a coefficient, and the sorting score is finally obtained. The obtained sorting scores not only consider the dimension condition of each fine screening of the first money receiving equipment under a single dimension, but also consider the cooperation among a plurality of first money receiving equipment, so that the finally obtained results are closer to the actual life, and the sorting scores are more accurate.

Further, it has been described above how to generate a chain of connected devices, and if the user follows the chain of connected devices, the user is likely to see the offline content delivered by the first merchant in the connected device repeatedly for many times. In this case, the user may be annoyed by some users.

Based on this, if it is determined that the second set has a connection device chain, the offline content corresponding to the delivery request sheet is divided into a plurality of content segments. For example, there is a part of the splicing devices in a certain splicing device chain (the part of the splicing devices is preferably continuous devices in the splicing device chain, which can achieve better effect, and certainly can achieve certain effect even if the part of the splicing devices is not continuous devices), and the video corresponding to the offline content is divided into a plurality of video segments according to the time sequence.

Matching with the plurality of content segments according to the sequence of the splicing devices in the splicing device chain, for example, one-to-one matching may be performed, or one splicing device matches the plurality of content segments to obtain a matching result, and delivering the content segments on the delivery device according to the matching result. Therefore, when the user goes forward according to the continuous equipment chain, the user sees the offline content which is not repetitive any more, but is similar to the fragments of the series, the interest of the user in continuously watching the offline content can be improved, the attention of the user to the offline content is also improved, and a better putting effect is obtained.

In one or more embodiments of the present disclosure, as described above, the second set of devices may further perform a refinement of business policies to select a more suitable delivery device. For ease of description, some or all of the second set of devices will be referred to herein as the second checkout device.

Specifically, the date of operation of the second merchant where the second payment apparatus is located is first determined, and whether the second merchant is a new store is determined according to the date of operation and the current date (for example, a merchant whose time difference between the date of operation and the current date is lower than a preset threshold is defined as a new store). If the second merchant is a new merchant, the new merchant can be preferentially selected from the second set of equipment according to a preset new-merchant support strategy so as to improve the enthusiasm of the newly-added second merchant.

Further, after the new store is determined, the business operation range corresponding to the second money receiving devices is continuously determined, and each second money receiving device may correspond to one or more business operation ranges. The business operation range can comprise a dining range, a clothing range, an entertainment range and the like, and can be further divided, such as a Chinese restaurant, a western restaurant, a cafeteria, a beverage shop and the like. And according to the business operation range and the business operation ranges of other collection equipment in the second set, the business cross range of the second collection equipment and other collection equipment can be obtained. As the extent of the service intersection decreases, it indicates that the specificity of the second payment device in the second set of devices increases, along with its irreplaceability in the second set of devices. Even when the service crossing range is 0, if there is a requirement that the user has a service operation range relation of the second collection device, only the second collection device can be accessed (of course, the collection device in the second collection device can also be accessed, but the analysis is not considered due to the prior fine screening dimension and the like). Therefore, as the service crossing range is reduced, the probability that the second cash collecting device is selected as the releasing device is increased, so that the user with the part of requirements can be ensured to release the offline content.

Based on the same idea, one or more embodiments of the present specification further provide apparatuses and devices corresponding to the above-described method, as shown in fig. 4 and 5.

Fig. 4 is a schematic structural diagram of an offline content delivery apparatus based on a payment receiving device according to one or more embodiments of the present disclosure, where the apparatus includes:

a receiving module 402, configured to receive a release request form sent by a release terminal of a first merchant;

a first screening module 404, configured to screen the payment receiving devices of a plurality of second merchants that are located around the drop terminal and that can receive orders, to form a first set of devices;

the performance data determining module 406 is configured to determine a plurality of fine screening dimensions according to a pre-constructed merchant related data set, and determine performance data of each first payment receiving device in the first device set in the fine screening dimensions;

the prediction module 408 determines a differentiated dimensionality and effect prediction scheme according to the relationship type between each fine screening dimensionality and the putting effect, and predicts a plurality of fine screening dimensionality scores for each first collection device respectively by combining the performance data;

a sorting score determining module 410, configured to determine a sorting score for each first payment apparatus according to the fine screening dimension scores for each first payment apparatus;

a second filtering module 412, configured to filter a part of the first cash collecting devices according to the sorting scores to form a second set of devices;

and a delivery module 414, configured to determine a delivery device of the offline content of the delivery request form in the second set of devices, and perform corresponding delivery.

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

determining a region code hash value to which the position of the commercial tenant IoT device where the releasing end is located belongs as a current hash value;

determining a plurality of surrounding area coding hash values as surrounding hash values according to the current hash value;

and according to the current hash value and the surrounding hash values, obtaining the money receiving equipment of a plurality of second merchants which can receive the order in the hash table by indexing to form a first set of equipment.

Optionally, the region-coded hash value is a geohash with a bit number not less than 5 bits, and the region-coded hash values are adjacent to the current hash value.

Optionally, the prediction module 408 determines, in each of the fine screening dimensions, a part of the fine screening dimensions that are in a negative correlation type with the putting effect as a negative correlation dimension set, and determines a part of the fine screening dimensions that are in a positive correlation type with the putting effect as a positive correlation dimension set;

and determining a differentiated dimensionality effect prediction scheme for the negative correlation dimensionality set and the positive correlation dimensionality set.

Optionally, the prediction module 408 determines a selection function according to the fine screening dimension, where 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, and performing normalization processing on the value of the fine screening dimension;

and determining a differentiated dimensionality effect prediction scheme for the negative correlation dimensionality set and the positive correlation dimensionality set by setting the differentiation of the threshold value and correspondingly converting the proportional property of the nonlinear transformation function.

Optionally, the set of negative correlation dimensions at least includes: a dimension representing a distance between a merchant IoT device where the releasing end is located and the first receiving device;

the positive correlation dimension set at least comprises: a dimension representing a number of cross-customers between the first merchant and the second merchant.

Optionally, the ranking score determining module 410 predicts a customer service connection probability between the first payment apparatuses according to the merchant related data set;

selecting a plurality of first collection devices from the first collection devices as connection devices according to the customer service connection probability;

determining a connection sequence among the connection devices to obtain one or more connection device chains, and determining a cooperative effect score of the connection device chains;

and for a first collection device in the continuous device chain, determining the sorting score of the first collection device according to the plurality of fine screening dimension scores and the cooperation effect score of the first collection device.

Optionally, the delivering module 414 determines whether the second set of devices includes the continuing device chain;

if so, segmenting the offline content of the release request list to obtain a plurality of content segments;

matching the sequence between the continuous devices in the continuous device chain with the sequence between the plurality of content segments to obtain a sequence matching result;

and determining the continuous equipment in the continuous equipment chain as the delivery equipment, and delivering the corresponding content segments on the corresponding delivery equipment according to the sequence matching result.

Optionally, the releasing module 414 determines an opening date corresponding to a second payment device in the second set of devices;

determining whether a second merchant corresponding to the second cash register device is a new store or not according to the operation date and the current date;

if yes, acquiring a business operation range corresponding to the second money receiving equipment;

determining the service cross range of the second collection device and other collection devices according to the service operation range of the second collection device and the service operation ranges of other collection devices in the second collection device;

and selecting a releasing device according to the service cross range, and increasing the probability that the second collection device is selected as the releasing device along with the reduction of the service cross range.

Fig. 5 is a schematic structural diagram of an offline content delivery device based on a payment receiving device according to one or more embodiments of the present disclosure, where the offline content delivery device includes:

at least one processor; and the number of the first and second groups,

Based on the same idea, one or more embodiments of the present specification further provide a non-volatile computer storage medium corresponding to the above method, and storing computer-executable instructions configured to:

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: the ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, 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.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, the present specification embodiments may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

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

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, 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 disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

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

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the embodiments of the apparatus, the device, and the nonvolatile computer storage medium, since they are substantially similar to the embodiments of the method, the description is simple, and for the relevant points, reference may be made to the partial description of the embodiments of the method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above description is merely one or more embodiments of the present disclosure and is not intended to limit the present disclosure. Various modifications and alterations to one or more embodiments of the present description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of one or more embodiments of the present specification should be included in the scope of the claims of the present specification.

Claims

1. An offline content delivery method based on a cash register device comprises the following steps:

2. The method according to claim 1, wherein the screening of the plurality of second merchant payment devices that are available for receipt around the dispensing end forms a first set of devices, and specifically comprises:

acquiring a hash table constructed according to a preset merchant IoT device set;

3. The method of claim 2, wherein the zone encoded hash value is a geohash having no less than 5 bits, and the zone encoded hash values are contiguous with the current hash value.

4. The method according to claim 1, wherein the step of determining a differentiated dimensional effect prediction scheme according to the type of relationship between each fine screening dimension and the delivery effect specifically comprises:

in each fine screening dimension, determining a part of fine screening dimensions which are in a negative correlation type with the feeding effect as a negative correlation dimension set, and determining a part of fine screening dimensions which are in a positive correlation type with the feeding effect as a positive correlation dimension set;

5. The method according to claim 4, wherein the determining a differentiated dimensionality effect prediction scheme for the negative correlation dimensionality set and the positive correlation dimensionality set specifically comprises:

determining 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;

6. The method of claim 4 or 5, wherein the set of negative correlation dimensions comprises at least: a dimension representing a distance between a merchant IoT device where the releasing end is located and the first receiving device;

7. The method of claim 1, wherein determining the respective ranking score for each of the first collection devices based on the respective fine-screen dimensional scores for each of the first collection devices comprises:

predicting the customer service connection probability among the first payment devices according to the merchant related data set;

8. The method according to claim 7, wherein the determining, in the second set of devices, a delivery device for the offline content of the delivery request ticket, and performing corresponding delivery specifically includes:

judging whether the second set of equipment contains the continuous equipment chain or not;

9. The method according to claim 1, wherein the determining, in the second set of devices, a delivery device for the offline content of the delivery request ticket specifically includes:

determining the opening date corresponding to the second money receiving device in the second set of devices;

10. An offline content delivery apparatus based on a cash register device, comprising:

11. The apparatus of claim 10, wherein the first filtering module obtains a hash table constructed according to a preset merchant IoT device set;

12. The apparatus of claim 11, wherein the zone encoded hash value is a geohash having no less than 5 bits, and the zone encoded hash values are contiguous with the current hash value.

13. The apparatus according to claim 11, wherein the prediction module, in each of the fine screening dimensions, determines a part of fine screening dimensions having a negative correlation with the delivering effect as a negative correlation dimension set, and determines a part of fine screening dimensions having a positive correlation with the delivering effect as a positive correlation dimension set;

14. The apparatus according to claim 13, wherein the prediction module determines a selection function according to a 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 settable threshold value when the value of the fine screening dimension is empty;

15. The apparatus according to claim 13 or 14, wherein the set of negative correlation dimensions comprises at least: a dimension representing a distance between a merchant IoT device where the releasing end is located and the first receiving device;

16. The apparatus of claim 10, wherein the ranking score determining module predicts a probability of continuation of customer service between the first payment devices based on the merchant-related data set;

17. The apparatus of claim 16, wherein the delivery module determines whether the second set of devices includes the continuing device chain;

18. The apparatus of claim 10, the placement module to determine an opening date for a second checkout device in the second set of devices;

19. An offline content delivery device based on a checkout device, comprising:

at least one processor; and the number of the first and second groups,