Copywriting generation method, device, electronic device and storage medium

Abstract

The present disclosure provides a method, device, electronic device and storage medium for generating copy, which relates to the field of natural language processing in the field of artificial intelligence technology. The specific implementation scheme is: obtaining a target text including action verbs in a landing page, intercepting the target text based on the action verbs to generate a text segment including action verbs, and determining the text segment that meets the fluency condition as the copy of the submit button in the landing page. The copy generation method disclosed in the present disclosure generates a text segment including action verbs by intercepting the target text based on action verbs, and determines the text segment that meets the fluency condition as the copy of the submit button in the landing page, which improves the richness of the copy of the submit button and more effectively meets the needs of various scenarios.

Description

Technical Field

[0001] The present disclosure relates to the field of natural language processing in the field of artificial intelligence technology, and in particular to a method, device, electronic device and storage medium for generating a copy. Background Art

[0002] At present, in the copy mining of Internet advertising business, by using traditional machine learning or deep learning methods, display text containing selling points is mined from creative copy or a copy generation model containing selling points is trained for use in the submission button copy of the landing page.

[0003] However, the richness of the submit button text is not high, and it is difficult to effectively meet the needs of various scenarios. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device and storage medium for generating a document.

[0005] According to a first aspect, a method for generating copy is provided, comprising: obtaining a target text including action verbs in a landing page; intercepting the target text based on the action verbs to generate a text segment including the action verbs; and determining the text segment that meets the fluency condition as the copy of a submit button in the landing page.

[0006] According to the second aspect, a copywriting generation device is provided, comprising: a first acquisition module, used to acquire a target text including action verbs in a landing page; a capture module, used to capture the target text based on the action verbs to generate a text segment including the action verbs; and a determination module, used to determine the text segment that meets the fluency condition as the copywriting of a submit button in the landing page.

[0007] According to a third aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for generating a document as described in the first aspect of the present disclosure.

[0008] According to a fourth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method for generating a document according to the first aspect of the present disclosure.

[0009] According to a fifth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the steps of the method for generating a document according to the first aspect of the present disclosure.

[0010] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0012] Figure 1 is a flowchart of a method for generating a copy according to the first embodiment of the present disclosure;

[0013] Figure 2 is a flowchart of a method for generating a copy according to a second embodiment of the present disclosure;

[0014] Figure 3 It is a schematic diagram of dependency parsing of a text segment;

[0015] Figure 4 This is a schematic diagram of the label definition of dependency parsing;

[0016] Figure 5 is a flowchart of a method for generating a copy according to a third embodiment of the present disclosure;

[0017] Figure 6 is a block diagram of a device for generating a text according to a first embodiment of the present disclosure;

[0018] Figure 7 is a block diagram of a device for generating a text according to a second embodiment of the present disclosure;

[0019] Figure 8 The block diagram of an electronic device used to implement the method for generating a copy of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. At present, AI technology has the advantages of high automation, high precision and low cost, and has been widely used.

[0022] Natural Language Processing (NLP) is a science that studies computer systems that can effectively implement natural language communication, especially the software systems therein. It is an important direction in the fields of computer science and artificial intelligence.

[0023] The following describes the copy generation method, device, electronic device and storage medium of the embodiments of the present disclosure in conjunction with the accompanying drawings.

[0024] Figure 1 It is a flowchart of a method for generating a copy according to the first embodiment of the present disclosure.

[0025] like Figure 1 As shown, the method for generating a copy in the embodiment of the present disclosure may specifically include the following steps:

[0026] S101, obtaining the target text including the action verbs in the landing page.

[0027] Specifically, the execution subject of the method for generating text in the embodiment of the present disclosure may be the text generation device provided in the embodiment of the present disclosure, and the text generation device may be a hardware device with data information processing capabilities and / or the necessary software required to drive the hardware device to work. Optionally, the execution subject may include a workstation, a server, a computer, a user terminal and other devices. Among them, the user terminal includes but is not limited to a mobile phone, a computer, an intelligent voice interaction device, a smart home appliance, a vehicle-mounted terminal, etc.

[0028] In the disclosed embodiment, the landing page is the page that the user enters after browsing and clicking on the advertisement, the action verb is the verb describing the user action in the landing page copy, such as obtain, receive, submit, etc., and the target text is the text including the action verb used for copy mining, and the target text including the action verb in the landing page is obtained for subsequent processing. For example, the target text can be "Beijing Welfare, Free Calculation of Income", where "calculation" is an action verb.

[0029] It is understandable to those skilled in the art that in the Internet advertising business, after browsing and clicking on an advertisement, a user will enter the advertisement's landing page, and the landing page is the last battlefield for advertisement conversion to occur, among which advertisement conversions include, for example, filling in contact information, making phone calls and online consultations, etc. Improving the conversion rate of the landing page is the ultimate goal of advertising.

[0030] S102: intercepting the target text based on the action verbs to generate a text segment including the action verbs.

[0031] Specifically, according to the target text including the action verb in the landing page obtained in step S101, the target text is intercepted based on the action verb to generate a text segment including the action verb.

[0032] S103, determining the text segment that meets the fluency condition as the copy of the submit button in the landing page.

[0033] Specifically, the smooth condition refers to the object corresponding to the action verb in the text segment, and the submit button is the button that the user needs to click when performing the action described by the action verb on the landing page. According to the text segment including the action verb generated in step S102, it is determined whether the text segment meets the smooth condition. If the text segment meets the smooth condition, the text segment that meets the smooth condition is determined as the text of the submit button in the landing page. It should be noted that the submit button is the most direct component for advertising conversion in the landing page, and the text of the submit button plays an important role in advertising conversion.

[0034] In summary, the copywriting generation method of the embodiment of the present disclosure obtains the target text including action verbs in the landing page, intercepts the target text based on the action verbs to generate a text segment including the action verbs, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page. The copywriting generation method of the present disclosure intercepts the target text based on the action verbs to generate a text segment including the action verbs, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page, which improves the richness of the copywriting of the submit button and more effectively meets the needs of a variety of scenarios.

[0035] Figure 2 It is a flowchart of a method for generating a copy according to the second embodiment of the present disclosure.

[0036] like Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, the method for generating a copy in the embodiment of the present disclosure may specifically include the following steps:

[0037] S201, obtaining candidate texts in the landing page.

[0038] Specifically, the candidate text is semantically complete candidate data, and the candidate text in the landing page is obtained for subsequent processing. It should be noted that the landing page contains rich text information, not only the text directly expressed in the advertisement, but also the rich text information in the accompanying pictures. Optionally, the semantically complete candidate data, i.e., the candidate text, can be obtained by parsing and cleaning the text and pictures of the landing page.

[0039] S202: Filter out target texts including action verbs from candidate texts according to the action verbs in the action verb vocabulary.

[0040] Specifically, the action verb vocabulary is a pre-set vocabulary consisting of multiple action verbs, and according to the action verbs in the action verb vocabulary, a target text including action verbs is screened out from the candidate texts obtained in step S201. For example, the target text is "Beijing Welfare, Free Calculation of Income", and the action verb in the target text is "calculation".

[0041] It should be noted that by using the action verb vocabulary to filter out texts containing action verbs from the candidate texts in the landing page, the pressure of subsequent word segmentation and syntactic analysis can be reduced, and the algorithm performance can be improved.

[0042] In the above embodiment, step S102 of “cutting the target text based on the action verbs to generate a text segment including the action verbs” may specifically include the following steps S203 - S205 .

[0043] S203: Perform word segmentation processing on the target text to generate a word segmentation result including a plurality of word segments.

[0044] Specifically, the target text in step S202 is segmented to generate a segmentation result including multiple segmentations. For example, as described in the above example, for the target text "Beijing welfare, free calculation of income", the segmentation result can be obtained as "Beijing welfare, free calculation of income".

[0045] It should be noted that the submit button text should not be too long. For example, the submit button text can be limited to a maximum of 8 Chinese characters. Therefore, it is necessary to perform word segmentation processing and subsequent part-of-speech tagging and word segmentation expansion on the target text.

[0046] S204, performing part-of-speech tagging on the words in the word segmentation results.

[0047] Specifically, part-of-speech tagging is performed on the part-of-speech tagging results of the multiple part-of-speech tagging results generated in step S203. For example, for the part-of-speech tagging result of the target text "Beijing welfare, free calculation of income", the tagging result obtained after part-of-speech tagging is "Beijing (place name) welfare (noun), (punctuation) free (verb adverb) calculation (verb) income (noun) (function word)".

[0048] S205, taking the action verb as the core, performing word segmentation expansion forward and backward until a break symbol is encountered to generate a text segment including the action verb.

[0049] Specifically, according to the part-of-speech tagging result of step S204, word segmentation expansion is performed forward and backward with the action verb as the core until encountering a break symbol, so as to generate a text segment including the action verb. It should be noted that the break symbol includes at least one of the following: punctuation, a word segment with a conjunction part of speech, and a word segment with a function word part of speech. Among them, the conjunction can be "and", "with", etc., and the function word can be "right", "right?", etc. For example, for the part-of-speech tagging result "Beijing (place name) welfare (noun), (punctuation) free (adverbial verb) calculate (verb) income (noun) right (function word)", with the action verb "calculate" as the core, word segmentation expansion is performed forward and backward. The forward expansion of "calculate" stops when encountering the break symbol ",", and the backward expansion of "calculate" stops when encountering the break symbol "right". Thus, the corresponding text segment including the action verb "calculate", "free calculate income", can be obtained.

[0050] Step S103 in the above embodiment, "determine the copywriting of the submit button in the landing page for the text segments that meet the smoothness condition", may specifically include the following steps S206 - S207.

[0051] S206, perform dependency syntax analysis on the text segment to generate a dependency syntax analysis result.

[0052] Specifically, perform dependency syntax analysis on the text segment including the action verb generated in step S205 to generate a dependency syntax analysis result. It should be noted that when inputting the text segment "free calculate income" including the action verb, the corresponding generated dependency syntax analysis result is as Figure 3 shown, and the label definition of the dependency syntax analysis is as Figure 4 shown.

[0053] S207, determine the text segment that meets the smoothness condition as the copywriting of the submit button according to the dependency syntax analysis result.

[0054] Specifically, according to the dependency syntax analysis result of the text segment generated in step S206, determine the text segment that meets the smoothness condition as the copywriting of the submit button. It should be noted that the present disclosure does not limit too much on the specific manner of determining the copywriting of the submit button according to the dependency syntax analysis result, and it can be set according to the actual situation.

[0055] As a possible implementation manner, determine the object of the action verb according to the dependency syntax analysis result, and determine the text segment including the object of the action verb as the copywriting of the submit button. For example, as Figure 3 and Figure 4 shown, it can be seen that the text segment "free calculate income" contains the core action verb "calculate", and at the same time contains the object "income" of the action verb "calculate", that is, the verb-object relationship (VOB). Therefore, it meets the smoothness condition, and the text segment "free calculate income" can be determined as the copywriting of the submit button.

[0056] In summary, the copywriting generation method of the embodiment of the present disclosure obtains candidate texts in the landing page, selects target texts including action verbs from the candidate texts according to the action verbs in the action verb vocabulary, performs word segmentation processing on the target text to generate a word segmentation result including multiple word segments, performs part-of-speech tagging on the word segments in the word segmentation result, performs word segmentation expansion forward and backward with the action verb as the core until a break character is encountered to generate a text segment including the action verb, performs dependency syntactic analysis on the text segment to generate a dependency syntactic analysis result, and determines the text segment that meets the fluency condition as the copywriting of the submit button according to the dependency syntactic analysis result. The copywriting generation method of the present disclosure generates a text segment including the action verb by intercepting the target text based on the action verb, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page, which improves the richness of the copywriting of the submit button and more effectively meets the needs of various scenarios. At the same time, the target text including action verbs is filtered through the action vocabulary, which improves the screening efficiency. The accuracy of the submit button copy is further improved by performing dependency syntax analysis on the text fragments.

[0057] Further, such as Figure 5 As shown, the above embodiment may further specifically include the following steps S501-S504 of generating an action verb vocabulary.

[0058] S501, obtain the copy in the sample landing page.

[0059] Specifically, the sample landing page is a landing page used as a sample for generating a vocabulary of action verbs, and the copy in the sample landing page is obtained for subsequent processing.

[0060] S502, obtaining verbs in the copy of the sample landing page.

[0061] Specifically, according to the copy in the sample landing page obtained in step S501, the verbs in the copy in the sample landing page are obtained for subsequent processing.

[0062] S503, filtering out action verbs from the verbs.

[0063] Specifically, according to the verbs in the copy of the sample landing page obtained in step S502, action verbs are screened out from the verbs in the copy. It should be noted that the present disclosure does not make too many restrictions on the specific method of screening action verbs, which can be set according to actual conditions.

[0064] As a possible implementation method, the word frequency of verbs is obtained, and action verbs are screened out from a preset number of verbs with the highest word frequency. The term frequency (tf) refers to the frequency of repeated appearance of words, i.e., verbs in the present disclosure, and the preset number refers to the number of required verbs that are preset. Optionally, the preset number can be 200, i.e., action verbs are screened out from the first 200 verbs. For example, the verbs are sorted in reverse order from high to low according to the word frequency, and these verbs are manually evaluated for suitability as action verbs, and marked as "good" or "bad", where verbs marked with "good" represent action verbs, such as obtaining, receiving, submitting, etc., and verbs marked with "bad" represent non-action verbs, such as verbs of direct sales, door-to-door services, and other business types.

[0065] S504: Generate an action verb vocabulary according to the screened multiple action verbs.

[0066] Specifically, according to step 503, action verbs are screened out from the verbs, and a corresponding action verb vocabulary can be generated.

[0067] Therefore, by selecting action verbs from the verbs in the copy in the sample landing page and generating an action verb vocabulary, the pressure of subsequent target text acquisition and interception is simplified, and the efficiency of submit button copy generation is improved.

[0068] Figure 6 It is a block diagram of a device for generating a text according to a first embodiment of the present disclosure.

[0069] like Figure 6 As shown, the text generation device 600 of the embodiment of the present disclosure includes: a first acquisition module 601, a capture module 602 and a determination module 603.

[0070] The first acquisition module 601 is used to acquire the target text including action verbs in the landing page.

[0071] The interception module 602 is used to intercept the target text based on the action verbs to generate a text segment including the action verbs.

[0072] The determination module 603 is used to determine the text segment that meets the fluency condition as the copy of the submit button in the landing page.

[0073] It should be noted that the above explanation of the embodiment of the method for generating a text is also applicable to the device for generating a text in the embodiment of the present disclosure, and the specific process will not be repeated here.

[0074] In summary, the copywriting generation device of the embodiment of the present disclosure obtains the target text including action verbs in the landing page, intercepts the target text based on the action verbs to generate a text segment including the action verbs, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page. The copywriting generation device of the present disclosure intercepts the target text based on the action verbs to generate a text segment including the action verbs, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page, which improves the richness of the copywriting of the submit button and more effectively meets the needs of various scenarios.

[0075] Figure 7 4 is a block diagram of a device for generating a text according to a second embodiment of the present disclosure.

[0076] like Figure 7 As shown, the text generation device 700 of the embodiment of the present disclosure includes: a first acquisition module 701, a capture module 702 and a determination module 703.

[0077] Among them, the first acquisition module 701 has the same structure and function as the first acquisition module 601 in the previous embodiment, the interception module 702 has the same structure and function as the interception module 602 in the previous embodiment, and the determination module 703 has the same structure and function as the determination module 603 in the previous embodiment.

[0078] Furthermore, the first acquisition module 701 may specifically include: a first acquisition unit, used to acquire candidate texts in the landing page; and a first screening unit, used to screen out target texts including action verbs from the candidate texts according to the action verbs in the action verb vocabulary.

[0079] Furthermore, the copy generation device 700 may specifically include: a second acquisition module 704, used to obtain the copy in the sample landing page; a third acquisition module 705, used to obtain the verbs in the copy in the sample landing page; a screening module 706, used to screen out action verbs from the verbs; and a generation module 707, used to generate an action verb vocabulary based on the screened multiple action verbs.

[0080] Furthermore, the screening module 706 may specifically include: an acquisition subunit, used to acquire the word frequency of verbs; and a screening subunit, used to screen out action verbs from a preset number of verbs with the highest word frequency.

[0081] Furthermore, the interception module 702 may specifically include: a word segmentation unit, which is used to perform word segmentation processing on the target text to generate a word segmentation result including multiple word segments; a tagging unit, which is used to perform part-of-speech tagging on the word segments in the word segmentation result; and an expansion unit, which is used to expand the word segments forward and backward with the action verb as the core until encountering an interruption symbol to generate a text segment including the action verb, wherein the interruption symbol includes at least one of the following: punctuation, a word segment whose part of speech is a conjunction, and a word segment whose part of speech is a function word.

[0082] Furthermore, the determination module 703 may specifically include: an analysis unit, configured to perform dependency syntactic analysis on the text segment to generate a dependency syntactic analysis result; and a determination unit, configured to determine the text segment that meets the fluency condition as the text of the submit button according to the dependency syntactic analysis result.

[0083] Furthermore, the determination unit may specifically include: a first determination subunit, used to determine the object of the action verb according to the dependency syntactic analysis result; and a second determination subunit, used to determine the text segment including the object of the action verb as the text of the submit button.

[0084] It should be noted that the above explanation of the embodiment of the method for generating a text is also applicable to the device for generating a text in the embodiment of the present disclosure, and the specific process will not be repeated here.

[0085] In summary, the copywriting generation device of the embodiment of the present disclosure obtains candidate texts in the landing page, selects target texts including action verbs from the candidate texts according to the action verbs in the action verb vocabulary, performs word segmentation processing on the target text to generate a word segmentation result including multiple word segments, performs part-of-speech tagging on the word segments in the word segmentation result, and performs word segmentation expansion forward and backward with the action verb as the core until a break character is encountered to generate a text segment including the action verb, performs dependency syntactic analysis on the text segment to generate a dependency syntactic analysis result, and determines the text segment that meets the fluency condition as the copywriting of the submit button according to the dependency syntactic analysis result. The copywriting generation device of the present disclosure generates a text segment including the action verb by intercepting the target text based on the action verb, and determines the text segment that meets the fluency condition as the copywriting of the submit button in the landing page, thereby improving the richness of the copywriting of the submit button and more effectively meeting the needs of various scenarios. At the same time, the target text including action verbs is filtered through the action vocabulary, which improves the screening efficiency. The accuracy of the submit button copy is further improved by performing dependency syntax analysis on the text fragments.

[0086] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0087] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0088] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0089] like Figure 8 As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0090] Multiple components in the electronic device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0091] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as Figures 1 to 5For example, in some embodiments, the method for generating the copy may be implemented as a computer software program, which is tangibly contained in a machine-readable storage medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the method for generating the copy described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to execute the method for generating the copy by any other appropriate means (e.g., by means of firmware).

[0092] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0093] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable document generation device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0094] In the context of the present disclosure, a machine-readable storage medium may be a tangible storage medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable storage medium may be a machine-readable signal storage medium or a machine-readable storage storage medium. A machine-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by digital data communication (e.g., a communication network) in any form or storage medium. Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0097] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0098] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the steps of the method for generating a document shown in the above embodiment of the present disclosure are implemented.

[0099] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0100] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating a copy, comprising: Get the target text including action verbs in the landing page; The target text is intercepted based on the action verb to generate a text segment including the action verb; as well as Performing dependency syntactic analysis on the text segment to generate a dependency syntactic analysis result; as well as Determining the object of the action verb according to the dependency syntactic analysis result; as well as The text segment including the object of the action verb is determined as the copy of the submit button in the landing page.

2. The generation method according to claim 1, wherein: The target text including the action verb in the landing page is obtained, including: Obtaining candidate text from the landing page; and According to the action verbs in the action verb vocabulary, the target text including the action verbs is screened out from the candidate texts.

3. The generation method according to claim 2, further comprising: Get the copy from the sample landing page; Obtain the verbs in the copy of the sample landing page; Filter out the action verb from the verbs; as well as The action verb vocabulary is generated according to the screened multiple action verbs.

4. The generation method according to claim 3, wherein: The step of selecting the action verb from the verbs includes: Obtaining the word frequency of the verb; and The action verbs are selected from the preset number of verbs with the highest word frequencies.

5. The generation method according to claim 1, wherein: The step of intercepting the target text based on the action verb to generate a text segment including the action verb includes: Performing word segmentation processing on the target text to generate a word segmentation result including a plurality of word segments; Performing part-of-speech tagging on the segmented words in the segmented word result; and The word segmentation is extended forward and backward with the action verb as the core until a break character is encountered to generate the text segment including the action verb, wherein the break character includes at least one of the following: punctuation, the word segment whose part of speech is a conjunction, and the word segment whose part of speech is a function word.

6. A copywriting generation device, comprising: The first acquisition module is used to acquire the target text including the action verb in the landing page; A cutting module, used for cutting the target text based on the action verb to generate a text segment including the action verb; as well as A determination module, configured to perform dependency syntactic analysis on the text segment to generate a dependency syntactic analysis result; and determining the object of the action verb according to the dependency syntactic analysis result; And determining the text segment including the object of the action verb as the copy of the submit button in the landing page.

7. The generating device according to claim 6, wherein: The first acquisition module includes: A first acquisition unit is used to acquire candidate texts in the landing page; and The first screening unit is used to screen out the target text including the action verb from the candidate texts according to the action verb in the action verb vocabulary.

8. The generating device according to claim 7, further comprising: The second acquisition module is used to obtain the copy in the sample landing page; A third acquisition module is used to acquire verbs in the copy of the sample landing page; A screening module, used for screening out the action verbs from the verbs; as well as A generating module is used to generate the action verb vocabulary according to the screened multiple action verbs.

9. The generating device according to claim 8, wherein: The screening module comprises: an acquisition unit, configured to acquire the word frequency of the verb; and The screening unit is used to screen out the action verbs from the preset number of verbs with the highest word frequency.

10. The generating device according to claim 6, wherein: The interception module comprises: A word segmentation unit, used for performing word segmentation processing on the target text to generate a word segmentation result including a plurality of word segments; a tagging unit, configured to perform part-of-speech tagging on the segmented words in the segmented word result; and The expansion unit is used to expand the word segmentation forward and backward with the action verb as the core until a break character is encountered to generate the text segment including the action verb, wherein the break character includes at least one of the following: punctuation, the word segmentation whose part of speech is a conjunction, and the word segmentation whose part of speech is a function word.

11. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 5.

Images