CN117033453A

CN117033453A - Coarse ranking method and device applied to recommendation system

Info

Publication number: CN117033453A
Application number: CN202310949305.6A
Authority: CN
Inventors: 陈云锋; 肖宇涵
Original assignee: Wuxian Shenghuo Beijing Information Technology Co ltd
Current assignee: Wuxian Shenghuo Beijing Information Technology Co ltd
Priority date: 2023-07-31
Filing date: 2023-07-31
Publication date: 2023-11-10

Abstract

The application relates to a coarse ranking method and a coarse ranking device applied to a recommendation system. The method comprises the following steps: based on service data of the materials to be sorted, acquiring mass fractions of each material to be sorted; grouping the materials to be sorted according to the labels based on the labels of the materials to be sorted, and sorting the materials to be sorted according to the mass fraction in each group; based on preference labels of users, carrying out mass fraction weighting on materials grouped and ordered according to the labels, and then reordering; and circularly extracting materials from each label group to serve as rough-row recommended materials until the number of the extracted materials is equal to a preset number, wherein the number of the extracted materials in the preferred label group of the user is larger than the number of the materials extracted from other label groups. The coarse arrangement method considers individuation of users and ensures diversity of final results.

Description

Coarse ranking method and device applied to recommendation system

Technical Field

The application relates to the technical field of computers, in particular to a coarse ranking method and device applied to a recommendation system.

Background

At present, materials such as commodities or posts are often required to be recommended to users, and a recommendation system is required to generate materials to be recommended. In general, many (hundreds of thousands) of materials that a recommendation system needs to sort may need to be sorted by coarse sorting and then fine sorting, where the coarse sorting functions: on the premise of ensuring certain accuracy, the candidate materials are rapidly sorted and reduced (hundreds of thousands are reduced to thousands). There are two common approaches to coarse ranking, one is a neural network-based double-tower model, and the other is a simple rule-based ranking, such as ranking according to the click rate of the materials.

However, both of the above methods have some drawbacks: the development period of the double-tower model of the neural network is long, and the manpower and financial resources are consumed; the sorting method based on simple rules is short in development period, but is not capable of achieving individuation and diversity. For example, ordering at click rate may be top ranked content that is a popular category, and the ordering results for different users are relatively similar, thus not personalized.

Disclosure of Invention

In order to overcome the problems in the related art, the embodiment of the application provides a coarse ranking method and a coarse ranking device applied to a recommendation system. The technical proposal is as follows:

according to a first aspect of an embodiment of the present application, there is provided a coarse ranking method applied to a recommendation system, including:

based on service data of the materials to be sorted, acquiring mass fractions of each material to be sorted;

grouping the materials to be sorted according to the labels based on the labels of the materials to be sorted, and sorting the materials to be sorted according to the mass fraction in each group;

based on preference labels of users, carrying out mass fraction weighting on materials grouped and ordered according to the labels, and then reordering;

and circularly extracting materials from each label group to serve as rough-row recommended materials until the number of the extracted materials is equal to a preset number, wherein the number of the extracted materials in the preferred label group of the user is larger than the number of the materials extracted from other label groups.

In an embodiment of the present application, the method further includes:

and when the preference labels of the users do not exist, circularly extracting materials from each label group which is sequenced according to the mass fraction to serve as recommended materials until the number of the extracted materials is equal to the preset number, wherein the number of the extracted materials in each label group is equal.

In one embodiment of the application, cyclically extracting material from each tag grouping comprises:

and carrying out de-duplication treatment on the materials extracted in the current cycle and the materials extracted in the last time.

In an embodiment of the present application, the obtaining the mass fraction of each material to be sorted based on the service data of the material to be sorted includes:

and calculating the mass fraction of each material to be sorted based on the plurality of pieces of service data and the respective preset weight coefficients of the plurality of pieces of service data.

According to a second aspect of an embodiment of the present application, there is provided a coarse arrangement device applied to a recommendation system, including:

the acquisition module is used for acquiring the mass fraction of each material to be sorted based on the business data of the material to be sorted;

the first sorting module is used for grouping the materials to be sorted according to the labels based on the labels of the materials to be sorted, and sorting the materials to be sorted according to the mass fraction in each group;

the second sorting module is used for carrying out mass fraction weighting on the materials which are grouped and sorted according to the labels based on the preference labels of the users and then re-sorting;

the first extraction module is used for circularly extracting materials from each label group to serve as rough-row recommended materials until the number of the extracted materials is equal to a preset number, wherein the number of the extracted materials in the preferred label group of the user is larger than the number of the materials extracted from other label groups.

In an embodiment of the application, the apparatus further comprises:

and the second extraction module is used for directly circularly extracting materials from each label group which is sequenced according to the mass fraction to serve as recommended materials when the preference labels of the user do not exist, and the number of the extracted materials is equal to the preset number, wherein the number of the extracted materials in each label group is equal.

In an embodiment of the present application, the first extraction module is configured to:

In an embodiment of the present application, the obtaining module is configured to:

According to a third aspect of embodiments of the present application, there is provided a coarse arrangement device applied to a recommendation system, including:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to:

According to a fourth aspect of embodiments of the present application there is provided a computer readable storage medium having stored thereon computer instructions which when executed by a processor implement the steps of the method of any of the first aspects of embodiments of the present application.

According to the technical scheme provided by the embodiment of the application, the materials are obtained through score calculation of the materials to be sorted, sorting in the sorting label group and sorting labels, the scores of the materials are weighted according to the preference of the user, the weight of the obtained number is weighted, individuation of the user is considered, and the diversity of the final result is ensured. Compared with a double-tower model of a neural network, the scheme can be developed and completed in 2-3 working days; the method is comprehensive in consideration of material quality, material diversity, user individuation, business weight and the like.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.

FIG. 1 is a flow chart illustrating a coarse ranking method applied to a recommendation system, according to an exemplary embodiment.

FIG. 2 is a flow chart illustrating a coarse ranking method applied to a recommendation system, according to an exemplary embodiment.

FIG. 3 is a block diagram illustrating a coarse arrangement applied to a recommendation system, according to an exemplary embodiment.

FIG. 4 is a block diagram illustrating a coarse arrangement applied to a recommendation system, according to an exemplary embodiment.

FIG. 5 is a block diagram illustrating a coarse arrangement applied to a recommendation system, according to an exemplary embodiment.

FIG. 6 is a block diagram illustrating a coarse arrangement applied to a recommendation system, according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.

Currently, the coarse-ranking method of the recommendation system has some defects: the development period of the double-tower model of the neural network is long, and the manpower and financial resources are consumed; the sorting method based on simple rules is short in development period, but is not capable of achieving individuation and diversity. The embodiment of the application provides a coarse ranking method applied to a recommendation system, which can be applied to terminals such as a server and a computer and can provide contents or commodities to be recommended for users. As shown in fig. 1, the method includes the following steps S101 to S103:

in step S101, a mass fraction of each material to be sorted is obtained based on the business data of the material to be sorted.

Different materials may have different business data. For example, for an e-commerce scenario, the material to be recommended to the user may be a commodity in the e-commerce, and the service data of the commodity may be data based on clicking, searching, collecting, purchasing, commenting, evaluating, and other actions, for example; for community scenarios, the material to be recommended to the user may be posts, blogs, etc., and the business data may be data based on click, comment, praise, forwarding, collection, attention, etc. behaviors, for example.

In an embodiment of the present application, for each material to be sorted, the mass fraction of the material may be calculated based on the plurality of pieces of service data and respective preset weight coefficients of the plurality of pieces of service data.

In step S102, the materials to be sorted are grouped according to the labels based on the labels of the materials to be sorted, and sorted according to the mass fraction in each group.

Each item has a label. For example, for merchandise, there may be tags such as "clothing," "shoes," "electronics," and the like. Each item may have one or more labels. For posts, there may be "movies", "delicacies", "star chasing". This step is grouping the materials based on the labels. When a material has two or more tags, the material may be present in two or more tag groups at the same time.

In step S103, the materials grouped and ordered by the labels are weighted by mass based on the user' S preference labels and then reordered.

The recommendation system provides different recommended materials for different users. For the user, if the user preference label is provided, the weight processing can be emphasized on the mass fraction of the material in the label group where the user preference label is located, so that the mass fraction of the material in the user preference label group is improved.

Since some material may be present in two or more tag groupings at the same time, the quality of the material may be improved as one of the tag groupings belongs to the user's preferred tag, and the ordering of the material in the other tag groupings may change, thus requiring the material in all groupings to be reordered.

In step S104, the materials are circularly extracted from each tag group as recommended materials until the number of extracted materials is equal to a preset number, wherein the number of extracted materials in the preferred tag group of the user is greater than the number of materials extracted from other tag groups.

In one embodiment of the present application, the material extracted in the current cycle is de-duplicated from the material extracted last time.

In the technical scheme of the application, the calculation of the score of the material is considered as the material quality and the service weight; sorting in the sub-label group, and obtaining materials by the sub-labels, wherein the diversity of the final result is considered; the scoring of the materials is weighted according to the user preference, and the weighting of the number is obtained, taking the individuation of the user into consideration. Compared with a double-tower model of a neural network, the scheme can be developed and completed in 2-3 working days; the method is comprehensive in consideration of material quality, material diversity, user individuation, business weight and the like.

In one embodiment of the application, the method further comprises the following step A1:

in step A1, when there is no preference label of the user, directly circularly extracting materials from each label group ordered according to the mass fraction as recommended materials until the number of extracted materials is equal to a preset number, wherein the number of extracted materials in each label group is equal.

The implementation is described in detail below by way of examples.

FIG. 2 is a schematic flow chart diagram illustrating a coarse ranking method applied to a recommendation system in accordance with an exemplary embodiment. The method may be performed by a server or a terminal providing a coarse-grained service. As shown in fig. 2, the method comprises the following steps:

in step S201, service data of the materials to be sorted is acquired.

The method may be performed when it is desired to recommend material for user a. As described above, different materials have different business data. In one embodiment of the application, the material to be sorted is, for example, a post. The traffic data of the posts includes click rate, praise rate, and forward rate.

In step S202, mass fractions of the materials to be sorted are calculated based on the plurality of pieces of service data and the preset weight coefficients of the plurality of pieces of service data.

And summarizing the service data of the posts based on different emphasis of the service to obtain the mass fraction of the material. In one embodiment of the application, the mass fraction may be calculated according to the following formula:

mass fraction=x click rate+y praise rate+z forward rate; wherein X, Y, Z is the preset weight of the business data-click rate, praise rate and forwarding rate respectively. The preset weight can be adjusted according to service emphasis.

In step S203, a label of the material to be sorted is acquired.

The material to be sorted may have only one tag and some material to be sorted may have multiple tags.

In step S204, the materials to be sorted are grouped according to the labels, and sorted according to the mass fraction in each group.

Firstly grouping the materials to be sorted according to the labels possessed by the materials, and then sorting the materials in the material group from high to low according to the mass fraction of S202. As shown in table one below, assume that the material to be ordered comprises: materials a, b, c, d, e, f, g, h, i, j, k, which have three labels in total: film, food and secondary element are finally ordered according to mass fraction as shown in the following table, wherein a is 0.8 for material a, and mass fraction is 0.8; material b has multiple tags, thus, material b is included in both the tags "movie" and "food" groupings

List one

Ordering/labeling	Film making apparatus	Food for delicacies	Two-dimensional element
				1	a:0.8	d:0.9	f:0.3
2	c:0.8	e:0.7	g:0.2
				3	j:0.7	b:0.6	i:0.1
4	b:0.6	k:0.1	g:0.0

In step S205, it is determined whether or not there is a preference tag of the user; if yes, go to step S206, if no, go to step S208.

In this step, it is determined whether the user a already has a preference tag.

In step S206, the materials grouped and ordered by label are weighted by mass based on the user' S preference label and reordered.

When the preference label of the user is plural, the higher the user ranking, the larger the weighting coefficient may be set for the weighting of the quality scores.

In this embodiment, it is assumed that user a has only one "movie" preference tag. In this embodiment, the mass fraction of material in the groupings of "movie" preference tags is weighted (say multiplied by a factor of 1.5) and reordered to obtain the data as shown in Table two, using a simple multiplicative weighting as an example.

Watch II

Ordering/labeling	Film making apparatus	Food for delicacies	Two-dimensional element
				1	a:0.8*1.5＝1.2	b:0.9	f:0.3
2	c:0.8*1.5＝1.2	d:0.9	g:0.2
				3	j:0.7*1.5＝1.05	e:0.7	i:0.1
4	b:0.6*1.5＝0.9	k:0.1	g:0.0

It should be noted that some materials may have multiple tags, as shown in table two above, material b belongs to a group of two tags, namely film and food, so the ordering under some tags may change after weighting, for example, material b under food tag ranks top.

In step S207, the materials are circularly extracted from the respective tag groupings as coarse-row recommended materials until the number of extracted materials is equal to a preset number, wherein the number of extracted materials in the user' S preferred tag groupings is greater than the number of materials extracted from other tag groupings.

In this embodiment, as previously described, user A has only one "movie" preference tab. When extracting material from the tag groupings of Table two each cycle, more material is extracted from the "movie" tag groupings, say 2, a specific number can be determined in conjunction with the business, while the number of extracted material in the other tag groupings remains 1. The specific process is as follows:

first round: 2 materials a and c are extracted from the 'film' tag grouping from high to low according to the sequence, 1 material b and f are extracted from the 'food' tag grouping from high to low according to the sequence, a set of { a, c, b and f } is obtained, and the next round is continued because the number 4 of the set is smaller than the preset number 5; wherein the preset number is to control the number of the final results and to ensure the quality of the content (the quality of the content after sorting is usually worse), here it is assumed that the preset number is 5;

a second wheel: extracting 2 materials j and b from a film tag group according to the sequence from high to low, extracting 1 material d and g from a food tag group and a two-dimensional tag group according to the sequence from high to low to obtain a set of { j, b, d and g } and carrying out de-duplication summarization on the set and { a, c, b, f, j, d and g } of the previous round to obtain { a, c, b, f, j, d and g }, and ending the circulation due to the fact that the number 7 of the set is larger than a preset number 5 to obtain a coarse-row recommended material { a, c, b, f, j, d and g }.

Therefore, the weighting mode enables the quantity of materials under the user preference label to be more in the rough-row recommended materials, and the weighting mode of the quality scores meets the individuation of the sorting to a certain extent.

In step S208, the materials are directly circularly extracted from the respective tag groupings sorted according to the mass fractions as recommended materials until the number of extracted materials is equal to a preset number, wherein the number of extracted materials in each tag grouping is equal.

In the step, materials are circularly extracted from each label group (shown in table one) which are ordered according to the mass fraction directly to serve as recommended materials, and when the materials are extracted, one material is extracted from high to low in each label group, and the weight is removed, so that the diversity of the screened materials can be ensured. Judging whether the number of the materials reaches the preset number or not after the circulation of all the label groups is completed each time, and stopping obtaining the materials. Specific:

first round: extracting 1 material from each label group of 'film', 'food', 'quadratic element' in table one to obtain the set of { a, d, f }, and continuing the next round because the number of sets is less than the preset number of 5.

A second wheel: extracting 1 material from each label group of 'film', 'food', 'quadratic element' in the table one to obtain a set of { c, e, g } and summarizing and de-duplicating { a, d, f } of the previous round to obtain { a, d, f, c, e, g }, and ending the cycle to obtain a coarse row of recommended materials { a, d, f, c, e, g }, wherein the number of the set 6 is greater than a preset number 5.

Because the recommendation system is finally provided with a fine ranking process and the like, the label grouping sequence of the coarse ranking recommended materials is not important, namely, whether the label grouping is firstly from a film label group or a food label group is firstly not important, and the obtained material set is unchanged.

According to the technical scheme adopted by the application, the calculation of the mass fraction of the material is considered as the material mass and the service weight; the materials are obtained by sorting in groups and sorting labels according to label grouping, and the diversity of the final result is considered. The scores of the materials are weighted according to the user preference, the weighting of the number is obtained, and the individuation of the user is considered. The scores and values are examples, and the specific values may be selected according to the actual service.

The following are examples of the apparatus of the present application that may be used to perform the method embodiments of the present application.

Fig. 3 is a block diagram illustrating a coarse arrangement device applied to a recommendation system according to an exemplary embodiment, where the coarse arrangement device applied to the recommendation system may be a server or a part of a server, or may be a terminal or a part of a terminal, and the coarse arrangement device applied to the recommendation system may be implemented as part or all of an electronic device through software, hardware, or a combination of both. As shown in fig. 3, the coarse arrangement device applied to the recommendation system includes:

the obtaining module 301 is configured to obtain a mass fraction of each material to be ordered based on service data of the material to be ordered;

the first sorting module 302 is configured to group the materials to be sorted according to the labels based on the labels of the materials to be sorted, and sort the materials to be sorted according to the mass fraction in each group;

a second sorting module 303, configured to perform mass-fraction weighting on the materials grouped and sorted according to the labels based on the preference labels of the user, and then reorder the materials;

the first extracting module 304 is configured to circularly extract materials from each tag group as coarse-row recommended materials until the number of extracted materials is equal to a preset number, where the number of extracted materials in the preferred tag group of the user is greater than the number of materials extracted from other tag groups.

In one embodiment, as shown in fig. 4, the apparatus further comprises:

and the second extracting module 305 is configured to directly circularly extract the materials from each label group ranked according to the mass fraction as recommended materials when the preference label of the user does not exist, until the number of the extracted materials is equal to the preset number, where the number of the extracted materials in each label group is equal.

In an embodiment, the first extraction module is configured to:

In an embodiment, the obtaining module is configured to:

FIG. 5 is a block diagram illustrating a coarse arrangement 50 for a recommender system, which may be a server or a portion of a server or a terminal or a portion of a terminal, according to an exemplary embodiment, comprising:

the processor 5001;

a memory 5002 for storing instructions executable by the processor 5001;

wherein the processor 5001 is configured to:

Fig. 6 is a block diagram illustrating a coarse arrangement 800, which may be a computer, server, etc., for a recommendation system, according to an exemplary embodiment.

The apparatus may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. Processing element 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to not store various types of data to support operations at the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.

The multimedia component 808 includes a screen between the device 800 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the apparatus 800 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the apparatus 800. For example, the sensor assembly 814 may detect an on/off state of the device 800, a relative positioning of the components, such as a display and keypad of the device 800, the sensor assembly 814 may also detect a change in position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, an orientation or acceleration/deceleration of the device 800, and a change in temperature of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 514 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as a private intercom network, wiFi,2G, 3G, 4G, or 5G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

A non-transitory computer readable storage medium, which when executed by a processor of apparatus 800, enables apparatus 800 to perform the coarse ranking method described above as being applied to a recommendation system, the method comprising:

Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A coarse ranking method applied to a recommendation system, comprising:

2. The method according to claim 1, wherein the method further comprises:

3. The method of claim 1, wherein cyclically extracting material from each tag grouping comprises:

4. The method of claim 1, wherein the obtaining a mass fraction of each material to be sorted based on the business data of the material to be sorted comprises:

5. A coarse arrangement device for a recommendation system, comprising:

6. The apparatus of claim 5, wherein the apparatus further comprises:

7. The apparatus of claim 5, wherein the first extraction module is to:

8. The apparatus of claim 5, wherein the acquisition module is configured to:

9. A coarse arrangement device for a recommendation system, comprising:

a processor;

a memory for storing processor-executable instructions;

wherein the processor is configured to:

10. A computer readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the steps of the method of any of claims 1-4.