Method, device, medium and electronic device for extracting key information of target object

By recognizing the target object's image and setting a scoring strategy, the problem of accurately extracting key information in existing technologies has been solved, achieving precise extraction of key information, and is suitable for tasks such as automatic generation of product marketing text.

CN112288548BActive Publication Date: 2024-11-19BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011272208.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-11-13
Publication Date
2024-11-19
Estimated Expiration
2040-11-13

AI Technical Summary

Technical Problem

Existing extractive automatic summarization technologies cannot meet the needs of automatic generation of product marketing texts, and it is difficult to extract key information of the target audience accurately.

Method used

By recognizing the image of the target object, a set of statements is obtained, and the statements are scored and selected according to the set scoring strategy, including scores for importance, specificity, readability, compliance and redundancy, until the number of selected statements reaches a set threshold, thus forming the key information of the target object.

Benefits of technology

It achieves relatively accurate extraction of key information from target objects, ensuring their importance, specificity, readability, compliance, and non-redundancy, and is suitable for downstream tasks such as automatic generation of product marketing text.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112288548B_ABST
    Figure CN112288548B_ABST
Patent Text Reader

Abstract

The embodiment of the present invention provides a method, device, medium and electronic device for extracting key information of a target object, and the extraction method includes the following steps: step S1, obtaining a first sentence set; step S2, scoring each sentence in the first sentence set according to a set scoring strategy; step S3, selecting a target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, and adding the target sentence to a second sentence set; step S4, repeating steps S2 and S3 until the number of words contained in the target sentence selected in step S3 is greater than or equal to a set first threshold; step S5, using the target sentence in the second sentence set obtained in step S4 as the key information of the target object. The technical solution of the embodiment of the present invention can obtain more accurate key information of the target object.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, computer-readable storage medium and electronic device for extracting key information of a target object. Background Art

[0002] In scenarios such as product marketing, it is necessary to extract key information about the product, such as extracting key text from the detailed text description of the product. Specifically, the detailed text of the product can come from the product details page image. After identifying the text in the product details page image, the key text is extracted from these large amounts of text to represent the characteristics of the product. This key text information can also be used for downstream tasks, such as automatic generation of product marketing text and e-commerce customer service Q&A and dialogue.

[0003] The task of extracting key information of a product is actually an extractive automatic summarization task, that is, extracting some text from the input text according to certain requirements as the output summary text.

[0004] In the downstream task of automatically generating product marketing texts, the extracted summary needs to be more targeted to make the product more attractive. However, the traditional extractive automatic summarization technology cannot meet the task requirements of automatically generating product marketing texts.

[0005] How to extract the key information of the target object more accurately is a technical problem that needs to be solved urgently.

[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0007] The purpose of the embodiments of the present invention is to provide a method, device, computer-readable storage medium and electronic device for extracting key information of a target object, thereby more accurately extracting the key information of the target object at least to a certain extent.

[0008] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0009] According to a first aspect of an embodiment of the present invention, a method for extracting key information of a target object is provided, the extraction method comprising the following steps: step S1, obtaining a first sentence set, the first sentence set consisting of sentences obtained by recognizing an image of the target object; step S2, scoring each sentence in the first sentence set according to a set scoring strategy to obtain a scoring score; step S3, selecting a target sentence with the highest scoring score in the first sentence set according to the scoring scores corresponding to each sentence, deleting the target sentence from the first sentence set and adding it to a second sentence set; step S4, taking steps S2 and S3 executed in sequence as a loop, and repeating the loop until the number of words contained in the target sentence selected in step S3 is greater than or equal to a set first threshold; step S5, taking the target sentences in the second sentence set obtained in step S4 except for the target sentence obtained by the last execution of step S3 as the key information of the target object.

[0010] In some embodiments, before step S1, the extraction method further includes: performing text recognition on the image of the target object by using OCR technology to obtain the first sentence set.

[0011] In some embodiments, the set scoring strategy includes: scoring the sentences in the first sentence set according to at least one of the following sentence attribute scoring rules: importance scoring rule, including scoring the importance of the current sentence according to the ratio of the font size of the current sentence to the font size of the sentence with the largest font in the image of the target object; specificity scoring rule, including scoring the current sentence according to the ratio of the number of specific keywords in the current sentence to the number of all words in the sentence, and determining the specific keywords according to the specificity key dictionary during the specificity scoring process; readability scoring rule, including scoring the readability of the current sentence according to the confidence of the current sentence given by the OCR recognition model during the OCR recognition of the image of the target object; compliance scoring rule, including scoring the compliance of the current sentence according to the ratio of the number of compliant words in the current sentence to the number of all words in the sentence, and determining the compliant words according to the non-compliant dictionary during the compliance scoring process; redundancy scoring rule, including scoring the redundancy of the current sentence according to the similarity between the current sentence and the sentences in the second sentence set;

[0012] In some embodiments, the set scoring strategy includes: taking the weighted sum of the scoring results of the importance score, the specificity score, the readability score, the compliance score and the redundancy score of the current sentence as the scoring score.

[0013] In some embodiments, the specific scoring rule includes a marketing scoring rule, which performs a marketing scoring on the current sentence according to a ratio of the number of marketing keywords in the current sentence to the number of all words in the sentence.

[0014] In some embodiments, before step S2, the extraction method further includes: establishing a specified key dictionary; and / or establishing a non-compliant dictionary.

[0015] In some embodiments, before step S2, the extraction method further includes: calculating the similarity between the current statement and each statement in the second statement set; and taking the maximum similarity among each of the similarities as the similarity between the current statement and the statements in the second statement set.

[0016] According to a second aspect of an embodiment of the present invention, there is provided a device for extracting key information of a target object, the device comprising: an acquisition unit, for acquiring a first sentence set, the first sentence set consisting of sentences obtained by recognizing an image of the target object; a scoring unit, for scoring each sentence in the first sentence set according to a set scoring strategy to obtain a scoring score; a selection unit, for selecting a target sentence with the highest scoring score in the first sentence set according to the scoring scores corresponding to each sentence, deleting the target sentence from the first sentence set and adding it to a second sentence set; a loop execution unit, for repeatedly executing a loop of scoring and selection operations performed in sequence by the scoring unit and the selection unit until the number of words contained in the target sentence selected by the selection unit is greater than or equal to a set first threshold; and an output unit, for using the target sentences in the second sentence set obtained after the loop execution unit is executed, except for the target sentence obtained by the last selection operation, as the key information of the target object.

[0017] According to a third aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method for extracting key information of a target object as described in the first aspect of the above embodiment is implemented.

[0018] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for extracting key information of the target object as described in the first aspect of the above embodiment.

[0019] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0020] In the technical solutions provided by some embodiments of the present invention, sentences are obtained by recognizing images of target objects, and the sentences are scored and selected according to a set scoring strategy to obtain key information of the target image that meets the requirements of the scoring strategy, thereby more accurately extracting the key information of the target object.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0023] Figure 1 A flowchart schematically shows a method for extracting key information of a target object according to an embodiment of the present invention;

[0024] Figure 2 A flowchart schematically shows a method for extracting key information of a target object according to another embodiment of the present invention;

[0025] Figure 3 A block diagram schematically shows a device for extracting key information of a target object according to an embodiment of the present invention;

[0026] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present invention will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0028] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or several hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0031] like Figure 1 FIG. 1 is a flow chart of a method for extracting key information of a target object according to an embodiment of the present invention. The method provided by the embodiment of the present invention can be executed by any electronic device with computer processing capabilities, such as a terminal device and / or a server. Figure 1 As shown, the method for extracting the key information of the target object includes:

[0032] Step S1, obtaining a first sentence set, where the first sentence set consists of sentences obtained by recognizing an image of a target object.

[0033] Step S2: Score each sentence in the first sentence set according to a set scoring strategy to obtain a scoring score.

[0034] Step S3, selecting the target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, deleting the target sentence from the first sentence set and adding it to the second sentence set.

[0035] Step S4, taking steps S2 and S3 executed in sequence as a loop, repeating the loop until the number of words contained in the target sentence selected in step S3 is greater than or equal to a set first threshold.

[0036] Step S5, taking the target sentences in the second sentence set obtained in step S4 except the target sentence obtained by the last execution of step S3 as the key information of the target object.

[0037] In the technical solution of the embodiment of the present invention, sentences are obtained by recognizing images, and the sentences are scored based on a set scoring strategy. After extracting the sentence with the highest score, the scoring and extraction operations are continued, and finally several sentences that are better and meet the word limit are obtained as the key information of the target object. In the process of extracting the key information, the key information is made more targeted based on the scoring strategy, so that the key information of the target object can be extracted more accurately.

[0038] Before step S1, the extraction method further includes: performing text recognition on the image of the target object by using OCR (Optical Character Recognition) technology to obtain a first sentence set.

[0039] Specifically, the target object in the embodiment of the present invention may be a product, and the first sentence set is a text data set. The text of these products comes from the product detail page pictures, which are obtained by recognizing the product detail page pictures through OCR technology.

[0040] In step S2, the scoring strategy set includes: scoring the sentences in the first sentence set according to at least one of the following sentence attribute scoring rules. These attribute scoring rules include: importance scoring rule, specificity scoring rule, readability scoring rule, compliance scoring rule and redundancy scoring rule.

[0041] In the embodiment of the present invention, modeling can be performed from five perspectives, namely, importance, specificity, readability, compliance, and redundancy, to score the statements in the first statement set.

[0042] In addition, the sentences in the first sentence set can also be scored from the perspective of word count limit. In this way, the extraction of key information of the target object can be restricted from six perspectives, namely importance, specificity, readability, compliance, redundancy and word count limit, so as to obtain key information of the target object that is important, marketing-oriented, fluent, compliant, non-redundant and meets the length limit.

[0043] From the perspective of word count limit, the first threshold is the length limit of the sentence, that is, the maximum number of words in the sentence. For example, the first threshold may be N, where N is a natural number. In this case, the length of the sentence with the highest score as the key information of the target object can only be less than N. In one embodiment, N may be 6, but is not limited thereto in practical applications.

[0044] In the embodiment of the present invention, the importance scoring rule may score the importance of the current sentence according to the ratio of the font size of the current sentence to the font size of the sentence with the largest font in the image of the target object.

[0045] Specifically, the sentence with the largest font size in each target object image is the theme sentence of the image, i.e., the title sentence. The score of the theme sentence of the image is 1, and the scoring formula for the importance score ai of other sentences other than the theme sentence is: ai = hi / hmax, where hi is the font size of the current sentence, hmax is the font size of the theme sentence, and i is a natural number, indicating the sequence number of the current sentence in the first sentence set.

[0046] For example, if the font size of a topic sentence in an image of a target object is 16 points, and the font size of a sentence of the target object is 12 points, the importance score of the sentence is 0.75.

[0047] In the embodiment of the present invention, the specificity scoring rule can perform a specificity scoring on the current sentence according to the ratio of the number of specific keywords in the current sentence to the number of all words in the sentence.

[0048] In one embodiment, the specified scoring rule may be a marketing scoring rule, in which the marketing scoring rule is used to perform a marketing scoring on the current sentence according to the ratio of the number of marketing keywords in the current sentence to the number of all words in the sentence.

[0049] In the process of specific scoring, specific keywords are determined according to the specific keyword dictionary; in the process of marketing scoring, marketing keywords are determined according to the marketing keyword dictionary. This requires the establishment of a specific keyword dictionary or a marketing keyword dictionary in advance.

[0050] For example, in the marketing scoring process, the marketing of a sentence is determined by the number of marketing keywords, i.e., selling point words, contained in the sentence. Whether a word is a selling point word is determined by a selling point dictionary. The selling point dictionary is a marketing key dictionary. The marketing key dictionary and selling point dictionary here can be annotated by experts.

[0051] For example, the scoring formula for the marketing score bi of a target object's sentence is: bi = #(mi) / #(Mi), where #(mi) is the number of words included in the marketing keyword dictionary of the current sentence, and #(Mi) is the total number of words in the current sentence.

[0052] The marketing value of a sentence indicates the proportion of marketing keywords in the sentence. When a sentence has 8 words, of which the number of marketing keywords is 4, the marketing value score of the sentence is 0.5.

[0053] In the embodiment of the present invention, the readability scoring rule may score the readability of the current sentence according to the confidence of the current sentence given by the OCR recognition model during the OCR recognition process of the image of the target object.

[0054] The scoring formula of the readability score ci is: ci = OCR confidence, ci represents the probability of accurate OCR recognition, and the OCR confidence is given by the OCR recognition model when recognizing the sentence in the image of the target object.

[0055] For example, in one embodiment, if the OCR confidence of a sentence is 0.8, the readability score of the sentence is 0.8.

[0056] In the embodiment of the present invention, the compliance scoring rule can score the compliance of the current sentence according to the ratio of the number of compliant words in the current sentence to the number of all words in the sentence. The compliance of the sentence indicates the ratio of compliant words in the sentence.

[0057] In the compliance scoring process, it is necessary to determine the compliant words based on the non-compliant dictionary, which requires the establishment of a non-compliant dictionary in advance.

[0058] For example, during the compliance scoring process, the compliance of a sentence is determined by the number of compliant words contained in the sentence. Whether a word is a compliant word is determined by the non-compliant dictionary. The non-compliant dictionary here can be defined by the content review team. Words in the non-compliant dictionary include pornography, gambling, drugs, or illegal advertising words. If a word is not found in the non-compliant dictionary, the word is compliant; if it can be found, the word is non-compliant.

[0059] For example, the scoring formula for the marketing score di of a target object is: di = #(ni) / #(Ni), where #(ni) is the number of words in the current sentence that are not included in the non-compliant dictionary, #(Ni) is the total number of words in the current sentence, and i is a natural number, representing the sequence number of the current sentence in the first sentence set.

[0060] The marketing value of a sentence indicates the proportion of legal words in the sentence. If a sentence has 8 words, of which 8 are not included in the non-compliant dictionary, the marketing value of the sentence is 0.5. The compliance score of the sentence is 1.

[0061] In the embodiment of the present invention, the redundancy scoring rule may perform a redundancy scoring on the current statement according to the similarity between the current statement and the statements in the second statement set.

[0062] The similarity between the current sentence and the sentences extracted from the second sentence set can be measured by the Jaccard similarity index. The calculation formula of the similarity ei between the current sentence and the sentences in the second sentence set can be: arg max k J(ti, tk), where J(ti, tk) is the Jaccard similarity index of two statements ti and tk, i is a natural number, indicating the sequence number of the current statement in the first statement set, and k is a natural number, indicating the sequence number of the statement in the second statement set.

[0063] When calculating the similarity between the current sentence and the sentences in the second sentence set, the similarity between the current sentence and each sentence in the second sentence set can be calculated, and the maximum similarity among each similarity is used as the similarity between the current sentence and the sentences in the second sentence set. That is, the similarity between the current sentence and the sentence with the maximum Jaccard similarity in the extracted second sentence set determines the redundancy of the current sentence. The greater the similarity between the current sentence and the sentences in the second sentence set, the greater the redundancy of the current sentence.

[0064] In one embodiment, when the similarities between the current statement and each statement in the second statement set are 0.8, 0.7, 0.6 and 0.65 respectively, the similarity score ei between the current statement and the statements in the second statement set is 0.8.

[0065] Furthermore, in an embodiment of the present invention, the set scoring strategy may be: taking the weighted sum of the scoring results of importance scoring, specificity scoring, readability scoring, compliance scoring and redundancy scoring of the current sentence as the scoring score.

[0066] For example, when the weights of all scoring results are 1, the calculation formula of the scoring score si can be: si = ai + bi + ci + di + ei. If the importance score of the current sentence is 0.75, the marketing score is 0.5, the readability score is 0.8, the compliance score of the sentence is 1, and the similarity score ei is 0.8, then the score si of the current sentence is 3.85.

[0067] By flexibly setting the weights of various parameters in the scoring formula, the influence of different sentence attributes on the sentence scoring results can be adjusted, thereby more flexibly selecting the key information of the target object.

[0068] In step S2, each statement in the first statement set needs to be scored according to the same scoring strategy to obtain the score of each statement. In step S3, the statement with the highest score among the statements in the first statement set is selected and added to the second statement set.

[0069] If the number of words included in the sentence selected in step S3 is less than the set first threshold, steps S2 and S3 are repeatedly executed until the number of words included in the sentence selected in step S3 is greater than or equal to the set first threshold.

[0070] It should be noted that when executing step S3 for the first time, a new second statement set needs to be created. Before each subsequent execution of step S2, the similarity between the current statement and each statement in the second statement set needs to be calculated, including the statement just added to the second statement set.

[0071] Therefore, when steps S2 and S3 are executed in a loop, the redundancy scores of the statements in the first statement set need to be recalculated each time.

[0072] In the embodiment of the present invention, when extracting sentences from the first sentence set, according to the calculation formula of the score of each sentence si=ai+bi+ci+di+ei, a greedy extraction method is adopted, that is, a sentence that has not been extracted and has the highest score is extracted each time, until the number of words in the extracted sentence reaches the length limit N. At this time, the last extracted sentence is excluded, and the set of other extracted sentences is the key information of the product.

[0073] The technical solution in the embodiment of the present invention proposes a method for extracting key information of goods based on extractive automatic summarization. In scenarios such as e-commerce, based on the characteristics of the scenarios, this method can be modeled from six perspectives, namely importance, marketing, readability, compliance, redundancy, and word limit, and use extractive automatic summarization technology to mine key information of goods and realize the extraction of key information of goods.

[0074] like Figure 2 As shown, in one embodiment of the present invention, the first threshold is taken as 6. The method for extracting key information of the target object in this embodiment includes the following steps:

[0075] Step S201, obtaining a first sentence set consisting of sentences obtained by recognizing an image of a target object.

[0076] Step S202: Score each sentence in the first sentence set according to a set scoring strategy to obtain a scoring score.

[0077] Step S203, selecting a target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, deleting the target sentence from the first sentence set and adding it to the second sentence set.

[0078] Step S204, determining whether the number of words in the target sentence selected in step S203 is greater than or equal to 6, if so, executing step S205; if not, executing step S202.

[0079] Step S205 , taking the target sentences in the second sentence set except the target sentence obtained by the last execution of step S203 as the key information of the target object.

[0080] In the method for extracting key information of a target object provided in an embodiment of the present invention, sentences are obtained by recognizing an image of the target object, and the sentences are scored and selected according to a set scoring strategy to obtain key information of the target image that meets the requirements of the scoring strategy, thereby achieving more accurate extraction of key information of the target object.

[0081] The following describes an embodiment of the device of the present invention, which can be used to execute the method for extracting key information of the target object described above. Figure 3 The device 300 for extracting key information based on a target object provided by the device embodiment of the present invention includes:

[0082] The acquisition unit 302 is used to acquire a first sentence set, where the first sentence set consists of sentences obtained by recognizing an image of a target object.

[0083] The scoring unit 304 is used to score each sentence in the first sentence set according to a set scoring strategy to obtain a scoring score.

[0084] The selection unit 306 is used to select the target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, delete the target sentence from the first sentence set and add it to the second sentence set.

[0085] The loop execution unit 308 is used to repeatedly execute the cycle of scoring and selecting operations performed in sequence by the scoring unit and the selecting unit until the number of words contained in the target sentence selected by the selecting unit is greater than or equal to a set first threshold.

[0086] The output unit 310 uses the target statements in the second statement set obtained after the loop execution unit is executed, except for the target statement obtained by the last execution of the selection operation, as the key information of the target object.

[0087] Since the various functional modules of the device for extracting key information based on the target object in the exemplary embodiment of the present invention correspond to the steps of the exemplary embodiment of the method for extracting key information of the target object mentioned above, for details not disclosed in the embodiment of the device of the present invention, please refer to the embodiment of the method for extracting key information of the target object mentioned above.

[0088] In the device for extracting key information based on a target object provided in an embodiment of the present invention, sentences are obtained by recognizing an image of the target object, and the sentences are scored and selected according to a set scoring strategy to obtain key information of the target image that meets the requirements of the scoring strategy, thereby achieving more accurate extraction of key information of the target object.

[0089] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system 400 of an electronic device suitable for implementing an embodiment of the present invention. Figure 4 The computer system 400 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0090] like Figure 4As shown, computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 404 into a random access memory (RAM) 403. Various programs and data required for system operation are also stored in RAM 403. CPU 401, ROM 402 and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0091] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.

[0092] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 409, and / or installed from the removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present application are executed.

[0093] It should be noted that the computer-readable storage medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable storage medium other than a computer-readable storage medium that can transmit, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0094] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0095] The units involved in the embodiments of the present invention may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, limit the units themselves.

[0096] As another aspect, the present application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method for extracting key information of the target object as described in the above embodiment.

[0097] For example, the electronic device can implement Figure 1 and Figure 2 The steps shown.

[0098] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into several modules or units to be embodied.

[0099] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0100] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed by the present invention. The specification and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0101] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for extracting key information of a target object, characterized in that: The extraction method comprises the following steps: Step S1, obtaining a first sentence set, wherein the first sentence set is composed of sentences obtained by recognizing the image of the target object; Step S2, scoring each statement in the first statement set according to a set scoring strategy to obtain a scoring score; Step S3, selecting the target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, deleting the target sentence from the first sentence set and adding it to the second sentence set; Step S4, taking steps S2 and S3 executed in sequence as a loop, and repeatedly executing the loop until the number of words contained in the target sentence selected in step S3 is greater than or equal to a set first threshold; Step S5, taking the target sentences in the second sentence set obtained in step S4 except the target sentence obtained by the last execution of step S3 as the key information of the target object.

2. The extraction method according to claim 1, characterized in that Before step S1, the extraction method further comprises: The first sentence set is obtained by performing text recognition on the image of the target object using OCR technology.

3. The extraction method according to claim 2, characterized in that The set scoring strategy includes: scoring the statements in the first statement set according to at least one of the following statement attribute scoring rules: An importance scoring rule includes scoring the importance of the current sentence based on a ratio of a font size of the current sentence to a font size of a sentence with the largest font in the image of the target object; The specificity scoring rule includes scoring the current sentence based on the ratio of the number of specific keywords in the current sentence to the number of all words in the sentence, and determining the specific keywords based on a specificity key dictionary during the specificity scoring process; A readability scoring rule includes scoring the readability of the current sentence according to the confidence of the current sentence given by the OCR recognition model during the OCR recognition of the image of the target object; A compliance scoring rule, comprising scoring the compliance of the current sentence according to a ratio of the number of compliant words in the current sentence to the number of all words in the sentence, and determining the compliant words according to a non-compliant dictionary during the compliance scoring process; The redundancy scoring rule includes scoring the redundancy of the current statement according to the similarity between the current statement and the statements in the second statement set.

4. The extraction method according to claim 3, characterized in that The set scoring strategy includes: The weighted sum of the respective scoring results obtained for the importance score, the specificity score, the readability score, the compliance score and the redundancy score of the current sentence is used as the scoring score.

5. The extraction method according to claim 4, characterized in that The specified scoring rules include marketing scoring rules, and the marketing scoring rules perform a marketing scoring on the current sentence according to a ratio of the number of marketing keywords in the current sentence to the number of all words in the sentence.

6. The extraction method according to claim 4, characterized in that Before step S2, the extraction method further comprises: Establishing a specified key dictionary; and / or, establishing a non-compliant dictionary.

7. The extraction method according to claim 4, characterized in that Before step S2, the extraction method further comprises: Calculating the similarity between the current sentence and each sentence in the second sentence set; The greatest similarity among the similarities is used as the similarity between the current sentence and the sentences in the second sentence set.

8. A device for extracting key information of a target object, characterized in that: The extraction device comprises: An acquisition unit, configured to acquire a first sentence set, wherein the first sentence set is composed of sentences obtained by recognizing the image of the target object; A scoring unit, used to score each statement in the first statement set according to a set scoring strategy to obtain a scoring score; A selection unit, configured to select a target sentence with the highest score in the first sentence set according to the score corresponding to each sentence, delete the target sentence from the first sentence set and add it to the second sentence set; A loop execution unit, used to repeatedly execute the cycle of scoring and selecting operations performed in sequence by the scoring unit and the selecting unit until the number of words contained in the target sentence selected by the selecting unit is greater than or equal to a set first threshold; The output unit uses the target statements in the second statement set obtained after the loop execution unit is executed, except for the target statement obtained by the last selection operation as the key information of the target object.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for extracting key information of a target object according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method for extracting key information of a target object as described in any one of claims 1 to 7.