Copywriting recommendation method and device

Abstract

Embodiments of the present specification provide a copywriting recommendation method and device, wherein a copywriting recommendation method comprises: obtaining an index table corresponding to a copywriting list and a historical recommendation number; calculating an index interval of the index table according to the number of index items of the index table and the historical recommendation number; selecting a target index item within the index interval and performing an exchange processing on the target index item and a boundary index item within the index interval; and performing copywriting recommendation on a target copywriting corresponding to the target index item in the copywriting list.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a copywriting recommendation method and apparatus. Background Technology

[0002] As the internet continues to develop and expand, the application scope of various services provided by the internet is also becoming wider and wider, gradually covering most users. In this context, service marketing through copywriting recommendations and other methods has become an effective means to improve user retention rates. However, in the process of recommending copywriting to users, repetitive copywriting recommendations may reduce the recommendation effect. Therefore, how to improve the effectiveness of copywriting recommendations has become a new challenge for service providers in the process of recommending copywriting to users. Summary of the Invention

[0003] This specification provides one or more embodiments of a copywriting recommendation method, including: obtaining an index table corresponding to a copywriting list and historical recommendation counts; calculating an index interval of the index table based on the number of index items in the index table and the historical recommendation counts; selecting a target index item within the index interval and swapping the target index item with a boundary index item within the index interval; and recommending copywriting based on the target copywriting item corresponding to the target index item in the copywriting list.

[0004] This specification provides one or more embodiments of a copywriting recommendation device, comprising: an index table acquisition module configured to acquire an index table corresponding to a copywriting list and historical recommendation counts; an index interval calculation module configured to calculate an index interval of the index table based on the number of index items in the index table and the historical recommendation counts; an index item selection module configured to select a target index item within the index interval and interchange the target index item with a boundary index item within the index interval; and a copywriting recommendation module configured to recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

[0005] This specification provides one or more embodiments of a copywriting recommendation device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: obtain an index table corresponding to a copywriting list and historical recommendation counts; calculate an index interval of the index table based on the number of index items in the index table and the historical recommendation counts; select a target index item within the index interval and swap the target index item with a boundary index item within the index interval; and recommend copywriting for the target copywriting corresponding to the target index item in the copywriting list.

[0006] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following process: obtaining an index table corresponding to a list of text entries and the number of historical recommendations; calculating an index interval of the index table based on the number of index items in the index table and the number of historical recommendations; selecting a target index item within the index interval and swapping the target index item with a boundary index item within the index interval; and recommending text entries corresponding to the target index item in the text list. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0008] Figure 1 A flowchart illustrating a copywriting recommendation method provided for one or more embodiments of this specification;

[0009] Figure 2 A schematic diagram of an index table provided for one or more embodiments of this specification;

[0010] Figure 3 A flowchart illustrating a copywriting recommendation method for sports service scenarios, provided for one or more embodiments of this specification.

[0011] Figure 4 A schematic diagram of a copywriting recommendation device provided for one or more embodiments of this specification;

[0012] Figure 5 This is a structural diagram of a copywriting recommendation device provided for one or more embodiments of this specification. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0014] This instruction manual provides an example of a copywriting recommendation method:

[0015] In real-world scenarios, many service scenarios require randomness in copywriting recommendations. They may even require that all copywriting in the list be selected and recommended before the next round of copywriting recommendations can be conducted. Furthermore, based on the above requirements for copywriting selection, the higher the efficiency of copywriting selection, the higher the efficiency of user access response through copywriting recommendations. Therefore, even higher demands are placed on the efficiency of copywriting selection.

[0016] To address this, the copywriting recommendation method provided in this embodiment, based on the correspondence between the copywriting list and the index table, utilizes the index table to achieve efficient index selection and rapid selection of copywriting from the copywriting list. This allows for more efficient and faster copywriting recommendation based on rapid copywriting selection. Specifically, during the index selection process in the index table, the index range of the index table is calculated based on the number of index items and the historical recommendation frequency. Index items are then selected within this calculated range to narrow the index range and improve indexing efficiency. Furthermore, by swapping the target index item selected in the index table with the boundary index items within the index range, duplicate index selections are avoided in subsequent copywriting recommendation processes. Based on this, the copywriting recommendation not only ensures that copywriting recommendations in the copywriting list are not duplicated but also improves recommendation efficiency while maintaining efficient index selection.

[0017] Step S102: Obtain the index table corresponding to the copy list and the historical recommendation count.

[0018] The document list mentioned in this embodiment refers to a list consisting of one or more documents. The index table refers to an index list consisting of one or more index items. This embodiment establishes a correspondence between the document list and the index table, and then uses the index selection in the index table to select documents from the document list based on this correspondence.

[0019] The historical recommendation count refers to the number of times that copywriting recommendations have been made for the copywriting in the current copywriting list. It should be noted that the historical recommendation count can be the total number of recommendations made in one or more recommendation rounds for the current copywriting list, or the number of recommendations made within a single recommendation round. The historical recommendation count is reset to zero after each recommendation round ends. Each recommendation round involves selecting one copywriting from the list for recommendation, and so on, until all copywriting in the list has been selected and recommended. For example, if the copywriting list contains 7 copywritings and the historical recommendation count is 8, it means that this is the first copywriting recommendation in the second recommendation round of the copywriting list. Alternatively, if the copywriting list contains 7 copywritings, the historical recommendation count is reset to zero after the first recommendation round ends, and the historical recommendation count is reset to zero for subsequent recommendations in the second recommendation round.

[0020] In specific service scenarios of application copywriting recommendation, different service scenarios may have different copywriting lists, and a single service scenario may also have multiple copywriting lists. To address this, in order to ensure a higher degree of matching between the copywriting recommended to the user and the service accessed by the user in the current service scenario, the copywriting list can be determined based on the service data of the user's service access. Specifically, in an optional method provided in this embodiment, the copywriting list is determined in the following way:

[0021] Obtain user service data within the service period of the target service;

[0022] Determine the service range that the service data matches under the first copy type of the target service, and query the copy list corresponding to the service range in the copy set of the first copy type;

[0023] And / or,

[0024] Read the list of texts under the second text type of the target service.

[0025] The first type of copywriting refers to a type of copywriting with multiple copywriting lists. These multiple copywriting lists form a copywriting set. Based on different user service data, different copywriting lists will correspond to different copywriting lists in the copywriting set. In the process of recommending copywriting for this type of copywriting, it is necessary to determine the copywriting list in the copywriting set that matches the user's service data based on the user's service data, and then make corresponding copywriting recommendations based on the determined copywriting list.

[0026] The second copywriting type refers to a copywriting type with a copywriting list. In this case, when recommending copywriting for this type of copywriting, it is only necessary to read the copywriting list of this type of copywriting and make the corresponding copywriting recommendations.

[0027] For example, during the process of a user accessing a sports service, the copy for the sports service includes a total of 5 types: periodic summary copy, sports keyword copy, landmark related copy, sports distance copy, and sports duration copy. Each of these 5 types of copy has a corresponding copy list.

[0028] Among them, the periodic summary copy, sports keyword copy, and landmark related copy belong to the first type of copy. Each of the three types has a copy set consisting of 7 copy lists. When recommending copy for any one of the three types, the user's sports data within a sports statistics period of the sports service is first obtained, and then a copy list that matches the user's sports data is selected from the copy set of any one type.

[0029] The two types of copywriting are exercise distance copywriting and exercise duration copywriting. Each type has its own copywriting list. When recommending copywriting for either type, the copywriting list of either type can be read.

[0030] In specific implementation, to ensure the validity of the obtained index table and historical recommendation counts, the index table can be checked during the acquisition process. This prevents anomalies in the obtained index table from affecting the recommendation effect or even preventing the recommendation of copywriting. In one optional implementation of this embodiment, the acquisition of the index table and historical recommendation counts for the copywriting list includes:

[0031] Check if the first index table in the storage space corresponding to the document list is empty;

[0032] If so, initialize the first index table and the corresponding first recommendation count based on the number of copy in the copy list, and obtain the index table and the historical recommendation count.

[0033] On the other hand, during the process of checking whether the first index table corresponding to the document list in the above-mentioned storage space is empty, there may be a situation where the first index table is not empty. In this case, in order to achieve efficient index selection by utilizing the index table, in an optional implementation of this embodiment, when the first index table is not empty, the first index table and the first recommendation count stored in the storage space are read as the index table and the historical recommendation count.

[0034] Optionally, the index entries in the index table are configured with index information; the copy identifier of the copy corresponding to the index entry in the copy list is the same as the index information of the index entry. The index information can be the content of the index entry; the copy identifier can be the position number of the copy in the copy list, or it can be the recommendation priority order number of the copy in the copy list.

[0035] For example, Figure 2 Index Table 1, as shown, contains 6 index entries, whose index information is as follows: "0", "1", "2", "3", "4", and "5". The position numbers of the 6 text entries in the corresponding text list are "A", "B", "C", "D", "E", and "F", respectively. The 6 text entries in the text list correspond to the 6 index entries in turn. The text entry with position number "A" corresponds to index entry "0" in the index table. If index entry "0" in the index table is selected, the text entry with position number "A" in the text list is selected and recommended to the user. Similarly, the text entry with position number "B" corresponds to index entry "1" in the index table, and the text entry with position number "F" corresponds to index entry "5" in the index table.

[0036] In practical applications, as service scenarios change, there may be additions or deletions to the text list. To ensure the index table can adapt to these changes, this embodiment detects changes in the text list and initializes the index table upon detection of such changes. Specifically, in one optional implementation, obtaining the index table corresponding to the text list includes:

[0037] Check whether the number of texts in the text list is equal to the number of index entries in the first index table read from the storage space;

[0038] If they are equal, the first index table shall be used as the index table.

[0039] If they are not equal, the first index table is initialized based on the number of text entries to obtain the index table. Here, initializing the first index table includes adding or deleting index entries in the first index table, so that the number of index entries in the first index table after adding or deleting index entries is consistent with the number of text entries in the text list, and that the index entries in the first index table correspond one-to-one with the text entries in the text list.

[0040] Furthermore, in specific implementations, the two methods for obtaining the index table corresponding to the copywriting list provided above can be combined. This avoids the copywriting recommendation effect being affected or even impossible due to anomalies in the obtained index table, while also ensuring that the index table can synchronize with changes in the copywriting list. Specifically, in one optional implementation of this embodiment, obtaining the index table corresponding to the copywriting list includes:

[0041] Check if the first index table in the storage space corresponding to the document list is empty;

[0042] If so, initialize the first index table according to the number of texts in the text list to obtain the index table;

[0043] If not, check whether the number of texts in the text list is equal to the number of index entries in the first index table;

[0044] If they are equal, the first index table shall be used as the index table.

[0045] If they are not equal, the first index table is initialized based on the number of texts to obtain the index table.

[0046] Step S104: Calculate the index range of the index table based on the number of index entries in the index table and the number of historical recommendations.

[0047] After obtaining the index table corresponding to the list of copywriting and the historical recommendation count, in this step, the index interval of the index table is calculated based on the number of index items in the index table and the historical recommendation count. Specifically, calculating the index interval based on the number of index items and the historical recommendation count can, on the one hand, narrow down the range of index selection in the index table and improve the efficiency of index selection, and on the other hand, constrain the selection of index items in the index table and reduce the possibility of index items being selected repeatedly in the same recommendation round.

[0048] In one optional implementation of this embodiment, the index range of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations, including:

[0049] The number of index entries in the index interval is calculated based on the number of index entries and the number of historical recommendations.

[0050] The set of consecutive index entries in the index table that contain boundary index entries of the index table is selected as the index interval according to the number of index entries.

[0051] Specifically, in selecting a set of index entries in the index table that are consecutive and contain boundary index entries of the index table, the index interval can be selected as the lower boundary index entries that are consecutive and lack the lower boundary (left boundary), or the index interval can be selected as the upper boundary index entries that are consecutive and lack the upper boundary (right boundary). The index interval refers to the range within the index table for selecting index entries.

[0052] For example, Figure 2 As shown in Index Table 2, if the number of index items obtained is 5, select 5 consecutive index items in Index Table 2, and the selected 5 consecutive index items include the lower boundary (left boundary) index item "0". The obtained index interval is the index interval composed of the 5 index items "0", "1", "2", "5", and "4".

[0053] For example, Figure 2 If the number of index items obtained from the calculated index table 4 is 3, and the selected 3 consecutive index items include the lower boundary index item "5" of the lower boundary (left boundary), the obtained index interval is the index interval composed of the 3 index items "5", "1", and "4".

[0054] Furthermore, in the process of calculating the number of index items in the index interval, the algorithm constraints can be used in conjunction with the index table to perform cyclical recommendations of different rounds for the same list of text entries. In one optional implementation of this embodiment, the number of index items in the index interval is calculated based on the number of index items and the number of historical recommendations, including:

[0055] The remainder is obtained by subtracting 1 from the number of historical recommendations and then dividing the remainder by the number of index entries in the index table.

[0056] The difference between the number of index entries in the index table and the remainder is used as the number of index entries in the index interval.

[0057] For example, the number of index entries can be calculated using the following formula:

[0058] Scope=indexList.size-{(times-1)%indexList.size}

[0059] Where Scope is the number of index items in the index range, indexList.size is the number of index items in the index table, and times is the number of historical recommendations.

[0060] Step S106: Select a target index item within the index interval and swap the target index item with the boundary index item within the index interval.

[0061] After determining the index range for index selection in the index table using the above steps, this step involves selecting a target index item within the index range. This allows for the recommendation of corresponding text in the text list based on the selected target index item. Furthermore, based on the selected target index item within the index range, the target index item is swapped with the boundary index item within the index range. This prevents index items in the index table from being selected repeatedly in the same recommendation round, which in turn prevents text in the text list from being recommended repeatedly in the same recommendation round.

[0062] In this embodiment, the target index item is selected within the index interval by using a random selection method. This ensures the randomness of the copywriting recommendations in the copywriting list, thereby enhancing the user's anticipation and interest in the copywriting recommendations. Specifically, in one optional implementation of this embodiment, selecting the target index item within the index interval includes: calling a random number generation algorithm to generate a random number, and selecting the index item whose index information within the index interval matches the random number as the target index item.

[0063] Based on selecting the target index item within the index interval, the target index item is swapped with the boundary index item within the index interval. In specific execution, the target index item and the boundary index item can be swapped in the index table, or the index information of the target index item and the index information of the boundary index item can be swapped. In this way, the number of times the index table is processed can be reduced, and the time complexity of processing the index table can be reduced.

[0064] As described above, in selecting a set of index entries that are consecutive and contain boundary index entries of the index table, the index interval can be selected from those containing consecutive lower boundary index entries (excluding the lower boundary, which is the left boundary) or those containing consecutive upper boundary index entries (excluding the upper boundary, which is the right boundary). Based on this, in the process of swapping the target index entry with the boundary index entries within the index interval, optionally, if the index interval contains lower boundary index entries, the target index entry is swapped with the upper boundary index entries within the index interval; if the index interval contains upper boundary index entries, the target index entry is swapped with the lower boundary index entries within the index interval.

[0065] For example, Figure 2The index table 1 shown contains all index entries in the index range. The target index entry randomly selected within the index range is index entry "3". Index entry "3" is then swapped with the upper boundary index entry "5" within the index range. The resulting index table is as follows: Figure 2 Index Table 2 is shown;

[0066] For example, Figure 2 Index table 4, as shown, has an index interval consisting of three index entries: index entry "5", index entry "1", and index entry "4". This index interval includes the lower boundary index entry "5". Therefore, after randomly selecting index entry "5" within the index interval, the positions of index entry "5" and the upper boundary index entry "4" within the index interval are swapped. The resulting index table is as follows: Figure 2 The index table shown is 5.

[0067] In specific implementation, after the target index item and the boundary index item within the index range are swapped, the index table stored in the storage space is updated using the swapped index table, and the historical recommendation count stored in the storage space is also updated. This ensures that subsequent recommendation processes can be based on the previous recommendation process, thereby avoiding duplication of index selection during the next copywriting recommendation process with the current index selection. Specifically, in an optional implementation provided in this embodiment, the swapped index table and historical recommendation count are updated and stored in the following manner:

[0068] The second index table obtained after the swapping process is stored in the storage space, and the index table stored in the storage space is updated with the second index table;

[0069] The historical recommendation count is updated to obtain a second recommendation count, and the historical recommendation count stored in the storage space is updated with the second recommendation count. Here, updating the historical recommendation count means incrementing the historical recommendation count by 1.

[0070] Step S108: Recommend copywriting for the target copywriting corresponding to the target index item in the copywriting list.

[0071] As described above, this embodiment establishes a correspondence between a text list and an index table. Based on this correspondence, it uses the index selection in the index table to select text from the text list. Therefore, after selecting the target index item from the index range of the index table, this step recommends text for the target text corresponding to the target index item in the text list.

[0072] In one optional implementation of this embodiment, copywriting recommendation is performed on the target copywriting corresponding to the target index item in the copywriting list, including:

[0073] Based on the target copy and the user's service data during the service period of the target service, a recommendation copy is generated;

[0074] Generate a service page carrying the recommended text and recommend it to the user.

[0075] Specifically, this embodiment provides the following two optional methods for generating recommendation text.

[0076] In the first optional implementation provided in this embodiment, recommended copy is generated based on the target copy and the user's service data during the service period of the target service, including:

[0077] Based on the motion records contained in the service data and the motion data corresponding to the location markers of the target text, calculate the text keywords;

[0078] The recommended copy is obtained by adding the keywords to the target copy.

[0079] For example, if a user's motion data includes a motion distance of m, and the motion distance corresponding to the landmark building in the target text is n, then m / n is calculated as the landmark keyword, and this landmark keyword is added to the target text to obtain the final recommended text to the user: "The motion distance is m, which is equivalent to circling the landmark building m / n times."

[0080] In the second optional implementation provided in this embodiment, recommended copy is generated based on the target copy and the user's service data during the service period of the target service, including:

[0081] Sort the motion records corresponding to each sub-cycle in the service data;

[0082] The recommended copy is obtained by combining the copy information based on the ranking results and the target copy.

[0083] For example, sort the user's daily exercise distance from largest to smallest, select the top-ranked distance, and combine it with the target text to obtain the final recommendation text to the user: "The exercise distance on this day was x, which is the longest day."

[0084] The following example uses a copywriting recommendation method provided in this embodiment to illustrate its application in a sports service scenario. Figure 3 For further explanation of the copywriting recommendation method provided in this embodiment, please refer to [link / reference]. Figure 3The copywriting recommendation method applied to sports service scenarios includes the following steps.

[0085] Step S302: Read the list of texts provided by the user in the sports service, as well as the index table and historical recommendation counts corresponding to the text list stored in the database.

[0086] Step S304: Determine if the index table is empty;

[0087] If so, proceed with steps S306 and S312 to S318;

[0088] If not, proceed to step S308.

[0089] Step S306: Initialize the index table and the number of historical recommendations based on the number of copy in the copy list.

[0090] Step S308: Check whether the number of texts in the text list is equal to the number of index entries in the index table;

[0091] If so, proceed to steps S312 to S318;

[0092] If not, proceed to steps S310 to S318.

[0093] Step S310: Initialize the index table based on the number of texts in the text list.

[0094] Step S312: Calculate the index interval based on the number of index entries in the index table and the number of historical recommendations.

[0095] Step S314: Select the target index item within the index range and swap the target index item with the boundary index item within the index range.

[0096] Step S316: Generate exercise recommendation copy based on the target copy and the user's exercise data during the exercise cycle.

[0097] Step S318: Generate a service page with exercise recommendation text and recommend it to the user.

[0098] The following is an example of a copywriting recommendation device provided in this manual:

[0099] In the above embodiments, a copywriting recommendation method is provided, and correspondingly, a copywriting recommendation device is also provided, which will be described below with reference to the accompanying drawings.

[0100] Reference Figure 4 The diagram shows a copywriting recommendation device provided in this embodiment.

[0101] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0102] This embodiment provides a copywriting recommendation device, including:

[0103] The index table acquisition module 402 is configured to acquire the index table corresponding to the copy list and the historical recommendation count;

[0104] The index interval calculation module 404 is configured to calculate the index interval of the index table based on the number of index entries in the index table and the number of historical recommendations.

[0105] The index item selection module 406 is configured to select a target index item within the index interval and swap the target index item with the boundary index item within the index interval.

[0106] The copywriting recommendation module 408 is configured to recommend copywriting for the target copywriting corresponding to the target index item in the copywriting list.

[0107] The following is an example of a copywriting recommendation device provided in this manual:

[0108] Corresponding to the copywriting recommendation method described above, based on the same technical concept, one or more embodiments of this specification also provide a copywriting recommendation device for executing the copywriting recommendation method provided above. Figure 5 This is a structural diagram of a copywriting recommendation device provided for one or more embodiments of this specification.

[0109] This embodiment provides a copywriting recommendation device, including:

[0110] like Figure 5 As shown, the copywriting recommendation device can vary significantly due to differences in configuration or performance. It may include one or more processors 501 and memory 502, and the memory 502 may store one or more application programs or data. The memory 502 may be temporary or persistent storage. The application programs stored in the memory 502 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions from the copywriting recommendation device. Furthermore, the processor 501 may be configured to communicate with the memory 502 and execute the series of computer-executable instructions from the memory 502 on the copywriting recommendation device. The copywriting recommendation device may also include one or more power supplies 503, one or more wired or wireless network interfaces 504, one or more input / output interfaces 505, one or more keyboards 506, etc.

[0111] In one specific embodiment, the copywriting recommendation device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the copywriting recommendation device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following:

[0112] Retrieve the index table corresponding to the copy list and the historical recommendation count;

[0113] The index range of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations.

[0114] Select a target index item within the index range, and swap the target index item with the boundary index item within the index range;

[0115] Recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

[0116] This specification provides an example of a storage medium as follows:

[0117] Corresponding to the copywriting recommendation method described above, based on the same technical concept, one or more embodiments of this specification also provide a storage medium.

[0118] The storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed by a processor, implement the following process:

[0119] Retrieve the index table corresponding to the copy list and the historical recommendation count;

[0120] The index range of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations.

[0121] Select a target index item within the index range, and swap the target index item with the boundary index item within the index range;

[0122] Recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

[0123] It should be noted that the embodiment of a storage medium in this specification and the embodiment of a recommended method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0124] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0125] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using a hardware physical module. For example, a Programmable Logic Device (PLD) (e.g., a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program a digital system themselves to "integrate" it onto a PLD, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0126] The controller can be implemented in any suitable manner. For example, it can take the form of 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, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, ASICs, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0127] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0128] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0129] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification 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, etc.) containing computer-usable program code.

[0130] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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 a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0131] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0134] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0135] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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 technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0136] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0137] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0138] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0139] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A copywriting recommendation method, comprising: Retrieve the index table corresponding to the copy list and the historical recommendation count; The number of index entries in the index interval of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations. The set of index entries in the index table that are consecutive and contain the boundary index entries of the index table is selected as the index interval according to the number of index entries in the index interval. Select a target index item within the index range, and swap the target index item with the boundary index item within the index range; Recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

2. The copywriting recommendation method according to claim 1, wherein obtaining the index table corresponding to the copywriting list and the historical recommendation count includes: Check if the first index table in the storage space corresponding to the document list is empty; If so, initialize the first index table and the corresponding first recommendation count based on the number of copy in the copy list, and obtain the index table and the historical recommendation count.

3. According to the copywriting recommendation method of claim 2, if the result of the execution of the sub-step "Whether the first index table corresponding to the copywriting list in the query storage space is empty" is no, the following operation is performed: Read the first index table and the first recommendation count stored in the storage space, and use them as the index table and the historical recommendation count.

4. The copywriting recommendation method according to claim 1, after the step of selecting a target index item within the index interval and swapping the target index item with the boundary index item within the index interval, further includes: The second index table obtained after the swapping process is stored in the storage space, and the index table stored in the storage space is updated with the second index table; The historical recommendation count is updated to obtain a second recommendation count, and the historical recommendation count stored in the storage space is updated with the second recommendation count.

5. The copywriting recommendation method according to claim 1, wherein obtaining the index table corresponding to the copywriting list includes: Check whether the number of texts in the text list is equal to the number of index entries in the first index table read from the storage space; If they are equal, the first index table shall be used as the index table. If they are not equal, the first index table is initialized based on the number of texts to obtain the index table.

6. The copywriting recommendation method according to claim 1, wherein the index entries in the index table are configured with index information; The copy identifier of the copy corresponding to the index item in the copy list is the same as the index information of the index item.

7. The copywriting recommendation method according to claim 6, wherein selecting a target index item within the index range includes: A random number generation algorithm is invoked to generate a random number, and an index item whose index information within the index range matches the random number is selected as the target index item.

8. The copywriting recommendation method according to claim 1, wherein calculating the number of index entries in the index range of the index table based on the number of index entries in the index table and the number of historical recommendations includes: The remainder is obtained by subtracting 1 from the number of historical recommendations and then dividing the remainder by the number of index entries in the index table. The difference between the number of index entries in the index table and the remainder is used as the number of index entries in the index interval.

9. The copywriting recommendation method according to claim 1, wherein the copywriting list is determined in the following manner: Obtain user service data within the service period of the target service; Determine the service range that the service data matches under the first copy type of the target service, and query the copy list corresponding to the service range in the copy set of the first copy type; And / or, Read the list of texts under the second text type of the target service.

10. The copywriting recommendation method according to claim 1, wherein recommending copywriting for the target copywriting corresponding to the target index item in the copywriting list includes: Based on the target copy and the user's service data during the service period of the target service, a recommendation copy is generated; Generate a service page carrying the recommended text and recommend it to the user.

11. The copywriting recommendation method according to claim 10, wherein generating recommended copywriting based on the target copywriting and the user's service data during the service period of the target service includes: Based on the motion records contained in the service data and the motion data corresponding to the location markers of the target text, calculate the text keywords; The recommended copy is obtained by adding the keywords to the target copy. or, Sort the motion records corresponding to each sub-cycle in the service data; The recommended copy is obtained by combining the copy information based on the ranking results and the target copy.

12. A copywriting recommendation device, comprising: The index table retrieval module is configured to retrieve the index table corresponding to the list of copywriting and the historical recommendation count; The index interval calculation module is configured to calculate the number of index entries in the index interval of the index table based on the number of index entries in the index table and the number of historical recommendations, and select the set of consecutive index entries in the index table that contain the boundary index entries of the index table as the index interval according to the number of index entries in the index interval; The index item selection module is configured to select a target index item within the index interval and swap the target index item with the boundary index item within the index interval. The copywriting recommendation module is configured to recommend copywriting for the target copywriting corresponding to the target index item in the copywriting list.

13. A copywriting recommendation device, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Retrieve the index table corresponding to the copy list and the historical recommendation count; The number of index entries in the index interval of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations. The set of index entries in the index table that are consecutive and contain the boundary index entries of the index table is selected as the index interval according to the number of index entries in the index interval. Select a target index item within the index range, and swap the target index item with the boundary index item within the index range; Recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

14. A storage medium for storing computer-executable instructions, which, when executed by a processor, perform the following process: Retrieve the index table corresponding to the copy list and the historical recommendation count; The number of index entries in the index interval of the index table is calculated based on the number of index entries in the index table and the number of historical recommendations. The set of index entries in the index table that are consecutive and contain the boundary index entries of the index table is selected as the index interval according to the number of index entries in the index interval. Select a target index item within the index range, and swap the target index item with the boundary index item within the index range; Recommend copywriting based on the target copywriting corresponding to the target index item in the copywriting list.

Images