Point of interest information updating method and apparatus, electronic device, and storage medium

Abstract

The present disclosure provides a point of interest information updating method and device, electronic equipment and storage medium, relates to the technical field of computers, and particularly to the technical field of computer vision and intelligent map. The specific implementation scheme is: obtaining a first image, determining a point of interest corresponding to the first image; in the case that the first image and the point of interest meet a preset condition, obtaining a second image of the point of interest according to time information of the first image; taking the first image and the second image as alternative images, determining a target image from each alternative image according to an identification confidence of each alternative image; and updating information of the point of interest based on target content obtained from the target image. With this scheme, the best quality image can be quickly determined from a large number of images, and then the identification result of the image is obtained by using the identification mode with the highest confidence, and the identification result is used to update the corresponding point of interest information, thereby ensuring the real-time and accuracy of the point of interest information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, in particular, to the technical field of computer vision and intelligent map, and specifically, to a point of interest information updating method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Point of Interest (POI) refers to all geographical objects that can be abstracted as a point, especially geographical entities closely related to people's lives, such as schools, banks, restaurants, hospitals, supermarkets, etc. In the field of electronic maps, map data updating is a common data processing operation. How to quickly obtain the latest POI data and improve the updating efficiency of map data to ensure the real-time and accuracy of map data is a hot issue in the field of intelligent map technology. SUMMARY

[0003] The present disclosure provides a point of interest information updating method and device, an electronic device, and a storage medium.

[0004] According to an aspect of the present disclosure, a point of interest information updating method is provided, which includes the following steps: obtaining a first image and determining a point of interest corresponding to the first image; in the case that the first image and the point of interest meet a preset condition, obtaining a second image of the point of interest according to time information of the first image; taking the first image and the second image as alternative images, determining a target image from the alternative images according to the recognition confidence of each alternative image; and updating the information of the point of interest based on the target content obtained from the target image.

[0005] According to another aspect of the present disclosure, a point of interest information updating device is provided, which includes: a first obtaining module configured to obtain a first image and determine a point of interest corresponding to the first image; a second obtaining module configured to obtain a second image of the point of interest according to time information of the first image in the case that the first image and the point of interest meet a preset condition; a determining module configured to take the first image and the second image as alternative images, and determine a target image from the alternative images according to the recognition confidence of each alternative image; and an updating module configured to update the information of the point of interest based on the target content obtained from the target image.

[0006] According to another aspect of the present disclosure, an electronic device is provided, which includes:

[0007] at least one processor; and

[0008] a memory connected to the at least one processor in communication; wherein

[0009] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method in any embodiment of the present disclosure.

[0010] According to another aspect of the present disclosure, a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method in any embodiment of the present disclosure is provided.

[0011] According to another aspect of the present disclosure, a computer program product comprising computer program / instructions is provided, wherein the computer program / instructions, when executed by a processor, implement the method in any embodiment of the present disclosure.

[0012] The technology of the present disclosure first determines a corresponding interest point through a first image obtained, and in the case that the interest point meets a preset update condition, obtains a plurality of images related to form a candidate image, then according to the confidence of each candidate image, obtains an optimal target image therefrom, and then updates the corresponding interest point according to the target content of the optimal target image. Through the above scheme, the optimal image of the interest point to be updated can be obtained from a large number of images, and then the target information is extracted from the optimal image for the update of the interest point, that is, the computing resources are saved, and the related information of the interest point can be quickly, accurately and timely updated.

[0013] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0014] The accompanying drawings are used to better understand the present scheme and do not constitute a limitation on the present disclosure. Among them:

[0015] Figure 1 is a flowchart of an interest point information update method according to an embodiment of the present disclosure;

[0016] Figure 2 is an image recognition schematic diagram according to an embodiment of the present disclosure;

[0017] Figure 3 is a flowchart of an interest point information update method according to another embodiment of the present disclosure;

[0018] Figure 4 is a schematic diagram of an interest point information update method according to still another embodiment of the present disclosure;

[0019] Figure 5 is a structural schematic diagram of an interest point information update device according to an embodiment of the present disclosure;

[0020] Figure 6 is a structural schematic diagram of a point of interest information updating device according to another embodiment of the present disclosure;

[0021] Figure 7 is a block diagram of an electronic device for implementing a point of interest information updating method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are set forth to assist in the understanding of the present disclosure. It should be apparent to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the spirit and scope of the present disclosure. Also, the description herein is merely illustrative of the present disclosure and does not limit the scope of the present disclosure. Therefore, the scope of the present disclosure should be defined by the appended claims.

[0023] The term "and / or", as used herein, merely describes association between associated objects, and can indicate three relationships, for example, A and / or B can indicate that A exists alone, A and B exist together, and B exists alone. The term "at least one of", as used herein, indicates any one of a plurality or at least any combination of at least two of a plurality, for example, includes at least one of A, B, and C can indicate any one or more elements selected from the set consisting of A, B, and C. The terms "first", "second", and the like, as used herein, indicate directions of similar technical terms and distinguish them, and do not mean a sequence or a meaning of only two, for example, a first feature and a second feature indicate two categories / two features, and the first feature can be one or more, and the second feature can also be one or more.

[0024] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following detailed description. Those skilled in the art will understand that the present disclosure can be implemented without certain specific details. In some examples, methods, means, elements and circuits well known to those skilled in the art are not described in detail in order to highlight the main idea of the present disclosure.

[0025] With the popularity of electronic maps containing POIs, how to accurately and efficiently obtain POI information has become a problem to be solved. For store-type POIs, the existing technology can obtain POI information by extracting information on the street photos. For example, for the telephone information of store-type POIs, it is statistically found that 30% of store signs contain telephone information. Therefore, if the telephone information in the photo of the store sign can be accurately extracted, the traditional manual input method can be eliminated, and the collection efficiency of telephone data can be greatly improved.

[0026] In the existing method, the actual collected image is often recognized by a general OCR (Optical Character Recognition) recognition engine, and then the target information (such as a telephone) in the image is produced by regular matching. However, the existing technology has the following disadvantages:

[0027] First, the actual collected store image is various, and in most cases, each store is collected more than 10 times in a year. It is difficult to select high-quality images from numerous collected images for the production and update of target content.

[0028] Second, the actual collected store image has various text contents, such as the image containing the store sign often containing the sign main name, business scope, advertisement, address, email and telephone, etc. It is difficult to accurately select the target content from numerous contents.

[0029] Third, most of the actual collected store images are taken by a driving recorder, the shooting distance is far, the image quality is low, and the existing text recognition method often cannot accurately extract the sign telephone information. If text recognition is performed on each low-quality image, it will undoubtedly cause waste of resources.

[0030] According to an embodiment of the present disclosure, a point of interest information updating method is provided, Figure 1 is a flowchart of a point of interest information updating method according to an embodiment of the present disclosure, specifically comprising:

[0031] S101: acquiring a first image and determining a point of interest corresponding to the first image;

[0032] In an example, the first image is an image related to a POI, which can be a photo taken on site by a person, a photo taken by a driving recorder, a photo taken by aerial photography, etc. The acquisition method of the first image is not limited here. The content of the first image can include the sign of the POI store, the facade of the POI, etc. The information of the first image is analyzed to determine the point of interest corresponding to the first image. Specifically, the POI matched with the first image can be obtained by matching the collection coordinates of the first image with the map information.

[0033] S102: acquiring a second image of the point of interest according to the time information of the first image in the case that the first image and the point of interest meet a preset condition;

[0034] In an example, it is first judged whether the point of interest meets the preset condition, and then it is judged whether the first image meets the preset condition in the case that the point of interest meets the preset condition.

[0035] In an example, in a case that the interest point is a to-be-updated interest point and the first image contains the target content, a second image of the interest point is acquired according to time information of the first image. The to-be-updated interest point needs to satisfy at least two conditions. First, the interest point is a valid interest point, i.e., the interest point belongs to an extractable industry. For example, a POI of a law-breaking store or a POI of a policy-related secret is not an extractable industry. The extractable industry can be confirmed by referring to an existing table. Second, the interest point is not updated too recently. For example, a month is set as a preset threshold, and it is determined whether the interest point is updated within the month. If the interest point is updated within the month, the interest point is not a to-be-updated interest point. Through the above scheme, the subsequent operation is performed on the premise that the interest point corresponding to the first image is a to-be-updated interest point, so that the image recognition of unnecessary updated interest points is prevented, and the redundant recognition work is reduced.

[0036] In an example, the specific steps of determining whether the first image contains the target content are as follows. First, at least two text recognition methods are used to determine whether the first image contains the target content, and at least two probability values are obtained. Then, it is determined whether the first image contains the target content according to the at least two probability values. Specifically, taking the target content as a telephone as an example, whether the telephone exists in the first image is recognized by at least two text recognition methods, such as layout analysis and OCR digital regular matching, and two probability values are obtained. The probability values are processed by a preset manner, such as taking a tie value or weighted addition. Then, it is determined whether the processed probability value exceeds a preset threshold. In a case that the threshold is exceeded, it is determined that the first image contains the target content, and the subsequent processing steps are allowed. Through the above steps, it can be accurately determined whether the first image contains the target content. If not, the subsequent detailed recognition is not performed, so that the resource occupation and time waste of the redundant recognition process are prevented.

[0037] In an example, the second image is obtained in the following manner, specifically comprising: first obtaining the acquisition time of the first image from the time information of the first image, and determining a time range according to the acquisition time; then taking the image of the POI that is acquired at the acquisition time meeting the time range as a preselected second image; specifically, according to the acquisition time of the first image, a preselected second image of the same POI is obtained, and the acquisition time of the preselected second image and the acquisition time of the first image meet a preset condition, for example, the time difference between the two acquisition times cannot exceed three weeks. Then, the preselected second image that has not been used to update the information of the POI is taken as the second image of the POI. With the above scheme, an image close in time to the first image is obtained as the second image, and then the image that has been used to update the POI is excluded. The remaining first and second images will be screened in subsequent steps to obtain the target image for updating the POI. This operation can obtain multiple relevant images close in time as candidate images for updating the POI, and exclude the images that have been used to update the POI, so as to prepare sufficient and non-repetitive materials for identifying the POI information, and improve the accuracy of the later identification and the efficiency of the entire identification process.

[0038] S103: taking the first image and the second image as candidate images, and determining a target image from the candidate images according to the recognition confidence of each candidate image;

[0039] In an example, as shown in FIG. 1, each candidate image (corresponding to the sign 1 to sign N in the figure) identifies the target information therein through multiple ways (layout analysis + text recognition), and finally determines the optimal image and obtains the target content therefrom. Through layout analysis, the recognition box type of each part in the image can be obtained, such as the POI name recognition box and the telephone recognition box shown in the figure. From the telephone recognition box, the recognition result of the target content, that is, the specific telephone number, can be obtained. In the specific operation, multiple ways are adopted for identification, and multiple recognition confidences are obtained. The multiple recognition confidences are weighted to obtain a final confidence, and then the optimal image is selected as the target image from the multiple candidate images according to the final confidence. Figure 2

[0040] S104: updating the information of the POI based on the target content obtained from the target image.

[0041] In an example, after obtaining the target content, the specific way of updating the information of the POI is determined according to the credibility of the content and whether it coincides with the information of the POI.

[0042] ​In an example, the step of obtaining the target content according to the recognition confidence includes: in a case where the recognition confidence meets a preset threshold, taking the recognition result corresponding to the recognition confidence as the target content; and in a case where the recognition confidence does not meet the preset threshold, taking a manual recognition result as the target content. In this way, if the optimal target image is selected, and even if the recognition confidence of the recognition method with the highest confidence does not meet the confidence standard, the image can be recognized manually. In this way, for a poor image, such as an image blocked by an obstacle, the image can be recognized manually to ensure the accuracy of the recognition result.

[0043] In an example, the step of obtaining the target content according to the recognition confidence includes: in a case where the recognition confidence meets a preset threshold, taking the recognition result corresponding to the recognition confidence as the target content; and in a case where the recognition confidence does not meet the preset threshold, taking a manual recognition result as the target content. In this way, if the optimal target image is selected, and even if the recognition confidence of the recognition method with the highest confidence does not meet the confidence standard, the image can be recognized manually. In this way, for a poor image, such as an image blocked by an obstacle, the image can be recognized manually to ensure the accuracy of the recognition result.

[0044] In an example, the step of obtaining the target content according to the recognition confidence includes: in a case where the recognition confidence meets a preset threshold, taking the recognition result corresponding to the recognition confidence as the target content; and in a case where the recognition confidence does not meet the preset threshold, taking a manual recognition result as the target content. In this way, if the optimal target image is selected, and even if the recognition confidence of the recognition method with the highest confidence does not meet the confidence standard, the image can be recognized manually. In this way, for a poor image, such as an image blocked by an obstacle, the image can be recognized manually to ensure the accuracy of the recognition result.

[0045] In an example, as shown in FIG. 3, the step S103 specifically includes: Figure 3

[0046] S301: Obtain a first recognition confidence of each of the candidate images, the first recognition confidence being obtained by performing text recognition on the candidate image; specifically, the text recognition method can be layout analysis or OCR digital regular matching, and the present disclosure does not limit the text recognition method.

[0047] ​S302: Extract the character features of the text recognition result of each candidate image, and obtain the second recognition confidence of each candidate image according to the matching degree of the character features and the preset character rule. Specifically, taking the extracted target content as a telephone as an example, after extracting the character features of each candidate image, it is judged whether the character features match the preset character rule of "telephone", such as whether the number of digits of the recognized characters in the image conforms to the number of digits of a common telephone, such as the number of digits of a mobile phone, whether the first digit of the characters is "1", etc.

[0048] S303: According to the obtained first recognition confidence and second recognition confidence, determine the target image from all candidate images, that is, perform data processing on the plurality of first recognition confidence and second recognition confidence to obtain a final confidence, and then select the optimal target image from the candidate images based on the final confidence. Through the above scheme, a plurality of recognition methods (such as combining OCR and layout analysis methods) are innovatively integrated, and the character preset rule is combined to select the optimal target image.

[0049] Application examples:

[0050] The application embodiment one processing flow includes the following contents, and the flowchart is as shown in Figure 4 In this embodiment, the target content is a shop telephone:

[0051] I. Collecting signboard images and table lookup filtering

[0052] In this step, it is mainly determined through table lookup whether the interest point corresponding to the signboard image meets the preset condition, including whether the interest point belongs to an extractable industry, or whether the last update time is within the preset time (such as within three months). If it is an unextractable industry, or there is an update within the preset time, subsequent operations are not performed.

[0053] II. Judging whether the signboard image includes the target content

[0054] This step is a preliminary analysis of the signboard image, and the layout analysis and OCR digital regular matching methods can be adopted to judge whether the signboard image includes a telephone. Among them, the OCR method can adopt the DBNET and ABINET models; the layout analysis can classify the text area on the signboard, such as distinguishing the name, telephone, business scope, advertisement and other areas, and in an example, the layout analysis adopts SOLOV2+LayoutXLM for area segmentation. If both kinds of analysis obtain a judgment result of including a telephone, the next step is performed.

[0055] III. Obtaining all related images within a preset time period

[0056] In this step, all images and their related information whether they are recognized are obtained by looking up the table, which meet the preset relationship with the real collected sign image, such as obtaining all images corresponding to the same interest point obtained in the past three months, and then determining whether these images are worked, i.e., whether they are used to read the phone number or update the information of the interest point. If all the obtained images are not worked, it is determined that the corresponding interest point is not extractable, and the images are not worked, and the work is abandoned. If all the obtained images are not worked, subsequent operations are performed on all the images. If some of the obtained images are worked, the images not worked are screened out, and the next step is performed.

[0057] This step is mainly taken considering that many related images are automatically collected by the driving recorders of vehicles, and there are a large number of repeated images, so it is necessary to filter the sign in a period of time and not to produce the phone number. In the actual system, a "regular matching + layout analysis" module is added, and the analyzed result is written into the sign library in real time, so that the related information can be directly obtained from the sign library in the phone production link, and subsequent operations can be performed, and it is not necessary to specifically identify every time.

[0058] Four, selecting the optimal sign image

[0059] In this step, the phone number is identified by using layout analysis and OCR on each sign image, and then the confidence of the layout analysis and the OCR is obtained. In addition, according to the identified result, the matching degree with the preset character rule is observed, such as the number of digits of the identified phone number, that is, the length of the number. The confidence of the layout analysis and the OCR and the length of the number are integrated and weighted to finally obtain the confidence of each image, and the optimal sign is selected according to the confidence.

[0060] Specifically, the candidate images can be sorted according to the confidence, and the sign images previously identified by manual recognition can be filtered out. The sign with better quality is selected from multiple signs, and is pushed to manual production or directly automatically produces the phone number.

[0061] Five, online phone number

[0062] According to the information of the optimal sign, the phone number on the sign is identified by automatic or manual way, and then the phone number is online, that is, the related information of the interest point is updated.

[0063] According to the disclosed embodiment, an interest point information updating device 500 is provided, Figure 5 is a structural schematic diagram of the interest point information updating device according to the embodiment of the present disclosure, as Figure 5 shown, comprising:

[0064] The first acquisition module 501 is used to acquire a first image and determine the interest point corresponding to the first image;

[0065] The second acquisition module 502 is used to acquire a second image of the point of interest based on the time information of the first image when the first image and the point of interest meet preset conditions.

[0066] The determining module 503 is used to use the first image and the second image as candidate images, and determine the target image from the candidate images based on the recognition confidence of each candidate image;

[0067] The update module 504 is used to update the information of the point of interest based on the target content obtained from the target image.

[0068] In one example, the second acquisition module 502 described above is used for:

[0069] If the point of interest is to be updated and the first image contains the target content, the second image of the point of interest is obtained based on the time information of the first image.

[0070] In one example, the second acquisition module 502 is further configured to: use at least two text recognition methods to determine whether the first image contains target content, and obtain at least two corresponding probability values;

[0071] The first image is determined to contain the target content based on at least two probability values.

[0072] In one example, the second acquisition module 502 described above is used for:

[0073] The acquisition time of the first image is obtained from the time information of the first image, and the time range is determined based on the acquisition time;

[0074] Images of the point of interest whose acquisition time falls within the specified time range will be used as the pre-selected second images.

[0075] The pre-selected second image that has not been used to update the information of the point of interest is used as the second image of the point of interest.

[0076] In one example, such as Figure 6 As shown, the determining module 503 includes:

[0077] The first confidence level acquisition unit 601 is used to acquire the first recognition confidence level of each candidate image, wherein the first recognition confidence level is obtained by performing character recognition on the candidate image using a character recognition method.

[0078] The second confidence obtaining unit 602 is configured to extract a character feature of the text recognition result of each candidate image, and obtain a second recognition confidence of each candidate image according to a matching degree of the character feature and a preset character rule.

[0079] The target determining unit 603 is configured to determine a target image from all candidate images according to the obtained first recognition confidence and second recognition confidence.

[0080] In an example, the updating module 504 is configured to:

[0081] obtain a recognition confidence of the target image;

[0082] obtain target content by using a preset recognition method according to the recognition confidence;

[0083] determine whether the target content is consistent with the information of the interest point;

[0084] update the information of the interest point by using the target content in a case where the target content is consistent with the information of the interest point.

[0085] The obtaining target content by using a preset recognition method according to the recognition confidence includes:

[0086] in a case where the recognition confidence meets a preset threshold, using a recognition result corresponding to the recognition confidence as the target content;

[0087] in a case where the recognition confidence does not meet the preset threshold, using an artificial recognition result as the target content.

[0088] The functions of each module in each device of the embodiments of the present application can be referred to the corresponding description in the above method, and will not be described here.

[0089] In the technical solutions of the present disclosure, the acquisition, storage and application of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0090] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0091] Figure 7A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0092] As shown in Figure 7 The device 700 includes a computing unit 701 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 702 or a computer program loaded into a random access memory (RAM) 703 from a storage unit 708. Various programs and data required for the operation of the device 700 can also be stored in the RAM 703. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0093] Various components in the device 700 are connected to the I / O interface 705, including an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, a magneto-optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0094] The computing unit 701 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized 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 701 performs various methods and processes described above, such as the point of interest information updating method. For example, in some embodiments, the point of interest information updating method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded onto the RAM 703 and executed by the computing unit 701, one or more steps of the point of interest information updating method described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform the point of interest information updating method by other any appropriate means, such as by means of firmware.

[0095] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0096] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0097] In the context of this disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0098] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0099] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0100] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0101] It should be understood that the various forms of flow shown above can be used to reorder, add, or remove steps. For example, the steps described in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, which is not limited herein.

[0102] The specific implementation described above does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for updating point-of-interest information, comprising: Acquire a first image and determine the points of interest corresponding to the first image; If the first image and the point of interest meet preset conditions, a second image of the point of interest is obtained based on the time information of the first image. The first image and the second image are used as candidate images, and the target image is determined from the candidate images based on the recognition confidence of each candidate image. The information of the points of interest is updated based on the target content obtained from the target image; When the first image and the point of interest meet preset conditions, obtaining a second image of the point of interest based on the time information of the first image includes: If the point of interest is a point of interest to be updated and the first image contains target content, a second image of the point of interest is obtained based on the time information of the first image. The step of obtaining the second image of the point of interest based on the time information of the first image includes: The acquisition time of the first image is obtained from the time information of the first image, and a time range is determined based on the acquisition time; Images of the points of interest whose acquisition time falls within the specified time range are used as pre-selected second images; The pre-selected second image that has not been used to update the information of the point of interest is used as the second image of the point of interest.

2. The method according to claim 1, further comprising: At least two text recognition methods are used to determine whether the first image contains target content, and at least two corresponding probability values ​​are obtained; The first image is determined to contain the target content based on the at least two probability values.

3. The method according to claim 1, wherein, The step of determining the target image from the candidate images based on the recognition confidence of each candidate image includes: The first recognition confidence score of each candidate image is obtained, wherein the first recognition confidence score is obtained by performing character recognition on the candidate image using a character recognition method; Extract the character features of the text recognition results of each candidate image, and obtain the second recognition confidence of each candidate image based on the degree of matching between the character features and the preset character rules; The target image is determined from all candidate images based on the obtained first and second recognition confidence scores.

4. The method according to claim 1, wherein, The step of updating the information of the point of interest based on the target content obtained from the target image includes: Obtain the recognition confidence score of the target image; Based on the recognition confidence level, a preset recognition method is used to obtain the target content; Determine whether the target content matches the information of the point of interest; If the target content matches the information of the point of interest, the information of the point of interest is updated using the target content.

5. The method according to claim 4, wherein, The step of obtaining the target content by adopting a preset recognition method based on the recognition confidence level includes: If the recognition confidence level meets the preset threshold, the recognition result corresponding to the recognition confidence level is taken as the target content; If the recognition confidence level does not meet the preset threshold, manual recognition is used and the result of manual recognition is used as the target content.

6. An apparatus for updating point-of-interest information, comprising: The first acquisition module is used to acquire a first image and determine the interest points corresponding to the first image; The second acquisition module is used to acquire a second image of the point of interest based on the time information of the first image when the first image and the point of interest meet preset conditions. The determination module is used to select the first image and the second image as candidate images, and determine the target image from the candidate images based on the recognition confidence of each candidate image; The update module is used to update the information of the point of interest based on the target content obtained from the target image; The second acquisition module is used for: If the point of interest is a point of interest to be updated and the first image contains target content, a second image of the point of interest is obtained based on the time information of the first image. The second acquisition module is used for: The acquisition time of the first image is obtained from the time information of the first image, and a time range is determined based on the acquisition time; Images of the points of interest whose acquisition time falls within the specified time range are used as pre-selected second images; The pre-selected second image that has not been used to update the information of the point of interest is used as the second image of the point of interest.

7. The apparatus according to claim 6, wherein the second acquisition module is further configured to: At least two text recognition methods are used to determine whether the first image contains target content, and at least two corresponding probability values ​​are obtained; The first image is determined to contain the target content based on the at least two probability values.

8. The apparatus according to claim 6, wherein, The determining module includes: The first confidence level acquisition unit is used to acquire the first recognition confidence level of each candidate image, wherein the first recognition confidence level is obtained by performing character recognition on the candidate image using a character recognition method; The second confidence level acquisition unit is used to extract the character features of the text recognition results of each candidate image, and obtain the second recognition confidence level of each candidate image based on the degree of matching between the character features and the preset character rules. The target determination unit is used to determine the target image from all candidate images based on the obtained first recognition confidence and second recognition confidence.

9. The apparatus according to claim 6, wherein, The update module is used for: Obtain the recognition confidence score of the target image; Based on the recognition confidence level, a preset recognition method is used to obtain the target content; Determine whether the target content matches the information of the point of interest; If the target content matches the information of the point of interest, the information of the point of interest is updated using the target content.

10. The apparatus according to claim 9, wherein, The step of obtaining the target content by adopting a preset recognition method based on the recognition confidence level includes: If the recognition confidence level meets the preset threshold, the recognition result corresponding to the recognition confidence level is taken as the target content; If the recognition confidence level does not meet the preset threshold, manual recognition is used and the result of manual recognition is used as the target content.

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 to enable the at least one processor to perform the method of any one of claims 1-5.

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

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

Images