Acquisition recommendation method and device, equipment and storage medium

Abstract

The invention relates to an album recommendation method and device, equipment and a storage medium. The method comprises the following steps: receiving chat data input by a user on a chat interface; determining at least one word segmentation result according to the chat data; searching album associated data to be recommended in an album database according to the word segmentation result; and sending the album associated data to a client, so that the client displays the album associated data on the chat interface. The method can effectively avoid the situation that the recommended content does not conform to the expectation of the user, and the accuracy and effectiveness of recommendation are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an album recommendation method, device, equipment and storage medium. Background Art

[0002] With the rapid development of science and technology, the wave of digitalization has changed the dissemination and consumption patterns of film and television albums. From television and movies to today's album playback platforms, albums have been integrated into daily life in a more convenient way and have become an important companion for people to relax. However, with the booming market, the number of film and television albums has increased sharply, and users are faced with a large number of albums and find it difficult to choose. Therefore, it has become particularly important to accurately recommend albums.

[0003] In practice, recommendations are often made to users based on the popularity of albums. Although popular albums have a broad audience base, each user has unique tastes. Recommendations based solely on popularity are difficult to accurately match the personalized preferences of each user, and the recommended albums often deviate from the user's expectations. Therefore, an album recommendation method is urgently needed. Summary of the invention

[0004] The present application provides an album recommendation method, apparatus, device and storage medium, which can effectively avoid the situation where the recommended content does not meet the user's expectations and significantly improve the accuracy and effectiveness of the recommendation.

[0005] In a first aspect, the present application provides an album recommendation method, the method comprising:

[0006] Receive chat data entered by the user in the chat interface;

[0007] Determine at least one word segmentation result according to the chat data;

[0008] According to the word segmentation result, searching the album-related data to be recommended in the album database;

[0009] The album-related data is sent to the client, so that the client displays the album-related data on the chat interface.

[0010] Optionally, determining at least one word segmentation result according to the chat data includes:

[0011] Detecting whether the chat data is voice data;

[0012] In the case where the chat data is voice data, converting the voice data into text data, and segmenting the text data using a preset word segmentation strategy to obtain at least one word segmentation result;

[0013] In the case where the chat data is text data, the preset word segmentation strategy is used to segment the text data to obtain at least one word segmentation result.

[0014] Optionally, the method further comprises:

[0015] According to the album database, a correspondence between entity ID, entity name and entity type is created to obtain at least one entity record;

[0016] The step of searching the album database for the album-related data to be recommended according to the word segmentation result includes:

[0017] Compare the word segmentation result with the entity name in each entity record to obtain a comparison result;

[0018] When the comparison result is a preset result, the album-related data to be recommended is determined based on the compared entity records.

[0019] Optionally, the method further includes:

[0020] Detecting whether an entity name in the entity record is a noise word;

[0021] When the entity name in the entity record is a noise word, the entity record is deleted.

[0022] Optionally, the method further includes:

[0023] Collect album reviews related to the album;

[0024] According to the album review, a reference vocabulary set is obtained;

[0025] For each entity record, based on the entity name in the entity record, it is detected in the reference vocabulary set whether there is an alias corresponding to the entity name. If there is an alias corresponding to the entity name, the entity name is associated with the alias to generate a new entity record.

[0026] Optionally, the method further includes:

[0027] For each entity record, a homophone name corresponding to each entity name is generated according to the entity name in the entity record, and the homophone name is associated with the entity name to generate a new entity record.

[0028] Optionally, the method further includes:

[0029] Get the entity name in the entity record to get the entity name set;

[0030] The word segmenter is updated according to the entity name set.

[0031] In a second aspect, the present application provides an album recommendation device, the device comprising:

[0032] A receiving unit, used to receive chat data input by the user in the chat interface;

[0033] A determination unit, configured to determine at least one word segmentation result according to the chat data;

[0034] A search unit, used for searching the album-related data to be recommended in the album database according to the word segmentation result;

[0035] The sending unit is used to send the album-related data to the client, so that the client displays the album-related data on the chat interface.

[0036] Optionally, the determining unit is used to:

[0037] Detecting whether the chat data is voice data;

[0038] In the case where the chat data is voice data, converting the voice data into text data, and segmenting the text data using a preset word segmentation strategy to obtain at least one word segmentation result;

[0039] In the case where the chat data is text data, the preset word segmentation strategy is used to segment the text data to obtain at least one word segmentation result.

[0040] Optionally, the device further includes a creation unit, wherein the creation unit is configured to:

[0041] According to the album database, a correspondence between entity ID, entity name and entity type is created to obtain at least one entity record;

[0042] The searching unit is used for:

[0043] Compare the word segmentation result with the entity name in each entity record to obtain a comparison result;

[0044] When the comparison result is a preset result, the album-related data to be recommended is determined based on the compared entity records.

[0045] Optionally, the device further comprises a detection unit, wherein the detection unit is configured to:

[0046] Detecting whether an entity name in the entity record is a noise word;

[0047] When the entity name in the entity record is a noise word, the entity record is deleted.

[0048] Optionally, the device further includes a first associating unit, wherein the first associating unit is configured to:

[0049] Collect album reviews related to the album;

[0050] According to the album review, a reference vocabulary set is obtained;

[0051] For each entity record, based on the entity name in the entity record, it is detected in the reference vocabulary set whether there is an alias corresponding to the entity name. If there is an alias corresponding to the entity name, the entity name is associated with the alias to generate a new entity record.

[0052] Optionally, the device further includes a second associating unit, wherein the second associating unit is configured to:

[0053] For each entity record, a homophone name corresponding to each entity name is generated according to the entity name in the entity record, and the homophone name is associated with the entity name to generate a new entity record.

[0054] Optionally, the device further includes an updating unit, wherein the updating unit is configured to:

[0055] Get the entity name in the entity record to get the entity name set;

[0056] The word segmenter is updated according to the entity name set.

[0057] In a third aspect, the present application provides an album recommendation device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to:

[0058] Receive chat data entered by the user in the chat interface;

[0059] Determine at least one word segmentation result according to the chat data;

[0060] According to the word segmentation result, searching the album-related data to be recommended in the album database;

[0061] The album-related data is sent to the client, so that the client displays the album-related data on the chat interface.

[0062] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the above-mentioned album recommendation method when executed by a processor.

[0063] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: in the embodiment of the present application, the chat data input by the user in the chat interface is received; at least one word segmentation result is determined based on the chat data; based on the word segmentation result, the album-related data to be recommended is searched in the album database; the album-related data is sent to the client, so that the client displays the album-related data on the chat interface. It can be seen that the present application can accurately match the film and television albums that the user is interested in from the user chat, provide intelligent and targeted album recommendation services, effectively avoid the situation where the recommended content does not meet the user's expectations, and significantly improve the accuracy and effectiveness of the recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0065] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0066] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0067] Figure 1 A flowchart of an album recommendation method provided in an embodiment of the present application;

[0068] Figure 2 A flowchart of a method for determining a word segmentation result provided in an embodiment of the present application;

[0069] Figure 3 A flowchart of a method for determining album-related data provided in an embodiment of the present application;

[0070] Figure 4 A flowchart of a method for identifying interference words provided in an embodiment of the present application;

[0071] Figure 5 A flowchart of an alias generation method provided in an embodiment of the present application;

[0072] Figure 6 A flowchart of a preset word segmentation strategy updating method provided in an embodiment of the present application;

[0073] Figure 7 A schematic diagram of a flow chart of an album recommendation device provided in an embodiment of the present application;

[0074] Figure 8 A schematic diagram of an album recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0076] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0077] With the rapid development of science and technology, the wave of digitalization has changed the dissemination and consumption patterns of film and television albums. From television and movies to today's album playback platforms, albums have been integrated into daily life in a more convenient way and have become an important companion for people to relax. However, with the booming market, the number of film and television albums has increased sharply, and users are faced with a large number of albums and find it difficult to choose. Therefore, it is particularly important to accurately recommend albums. In practice, users are often recommended based on the popularity of the album. Although popular albums have a wide audience base, each user's taste is unique. It is difficult to accurately match the personalized preferences of each user based solely on popularity. The recommended albums often deviate from the user's expectations.

[0078] In an embodiment of the present application, an album recommendation platform is provided in the album playback platform, and its main function is to recommend album-related data to users. In addition, the album recommendation platform can also determine whether to recommend album-related content to users based on the chat data entered by the user in the chat interface. The chat interface here can be an interface for users to communicate and interact with other users, or it can be a window for users to talk to AI. Once the chat data is monitored in the chat interface, the album recommendation platform will quickly determine whether to recommend album-related data to the user. In this way, this solution can accurately match the film and television albums that users are interested in from the user chat, provide intelligent and targeted album recommendation services, effectively avoid the situation where the recommended content does not meet user expectations, and significantly improve the accuracy and effectiveness of the recommendation.

[0079] In summary, the embodiments of the present application provide an album recommendation method, which can effectively avoid the situation where the recommended content does not meet the user's expectations and significantly improve the accuracy and effectiveness of the recommendation. Figure 1 As shown, the specific steps include:

[0080] Step 101, receiving chat data input by the user in the chat interface.

[0081] The chat data may be text data or voice data, which is not limited here.

[0082] In this step, when the user inputs chat data in the chat interface, the client obtains the chat data and sends it to the album recommendation platform, so that the album recommendation platform receives the chat data input by the user in the chat interface.

[0083] Among them, albums include various forms such as music and videos, including videos such as TV series and movies. The album recommendation platform is a component of the album playback platform. Its main function is to accurately recommend relevant albums to users based on the content input by users.

[0084] Step 102: Determine at least one word segmentation result based on the chat data.

[0085] In this step, since the chat data may be voice data or text data, it is necessary to first detect whether the chat data is text data or voice data. When the chat data is text data, the text data is directly segmented to obtain at least one word segmentation result. When the chat data is voice data, the voice data can be first converted into text data, and then the text data is segmented to obtain at least one word segmentation result. In this step, the voice data can be converted into text data using a speech recognition model, or other methods can be used to convert the voice data into text data, which is not limited here.

[0086] Step 103: Search the album database for album-related data to be recommended based on the word segmentation result.

[0087] The album-related data may be the album to be recommended, or may be information such as roles and actors related to the album, which is not limited here. Preferably, the album-related data is the album to be recommended.

[0088] In this step, the album-related data included in the album database is determined, and then the word segmentation data is compared with the album-related data to determine the album-related data to be recommended.

[0089] Step 104, sending the album-related data to the client, so that the client displays the album-related data on the chat interface.

[0090] In this step, after determining the album-related data to be recommended, the album-related data can be sent to the client, so that the client displays the album-related data in the chat interface. By this method, targeted recommendations can be implemented for users.

[0091] For example, album-related data is a certain album and a corresponding link, so that the album and the corresponding link are displayed on the chat interface. In this way, when the user clicks the link, the album can be accessed. Alternatively, album-related data is a series of albums starred by a certain actor and corresponding links, and these albums are sorted by popularity. In this way, the user can access a certain album according to a certain link.

[0092] In the embodiment of the present application, chat data input by the user in the chat interface is received; at least one word segmentation result is determined based on the chat data; based on the word segmentation result, the album-related data to be recommended is searched in the album database; the album-related data is sent to the client, so that the client displays the album-related data on the chat interface. It can be seen that the present application can accurately match the film and television albums that the user is interested in from the user chat, provide intelligent and targeted album recommendation services, effectively avoid the situation where the recommended content does not meet the user's expectations, and significantly improve the accuracy and effectiveness of the recommendation.

[0093] In an embodiment of the present application, when the chat data is only text data, there are two situations: one is that the user directly inputs text; the other is that the user inputs voice data, which is converted by the client into text data. In either case, the chat data received by the album recommendation platform is text data. In another case, once the client receives the chat data, it sends it directly to the album recommendation platform. At this time, the album recommendation platform needs to determine whether the received chat data is voice data. If it is voice data, it is first converted into text data, and then the text data is segmented to obtain at least one word segmentation result. Therefore, an embodiment of the present application provides a method for determining a word segmentation result, such as Figure 2 As shown, the specific steps include:

[0094] Step 201, detecting whether the chat data is voice data.

[0095] Among them, the voice data is the voice input by the user in the chat interface.

[0096] In this step, a pre-trained speech recognition model may be used to detect whether the chat data is voice data, or other methods may be used to detect whether the chat data is voice data, which is not limited here.

[0097] Step 202: when the chat data is voice data, convert the voice data into text data, and segment the text data using a preset word segmentation strategy to obtain at least one word segmentation result.

[0098] Among them, the preset word segmentation strategy is used to divide the continuous text sequence into individual words or phrases. The preset word segmentation strategy can be a rule-based word segmentation method, a statistics-based word segmentation method, a deep learning-based word segmentation method, etc., which is not limited here.

[0099] In this step, when the chat data is voice data, a pre-trained voice conversion model is used to convert the voice data into text data, and a preset word segmentation strategy is used to segment the text data to obtain at least one word segmentation result.

[0100] Step 203: When the chat data is text data, a word segmenter is used to segment the text data to obtain at least one word segmentation result.

[0101] Among them, the text data is the text entered by the user in the chat interface.

[0102] In an embodiment of the present application, the album recommendation platform can obtain data from the album database, create entity records, and then compare the word segmentation results with the entity names in each entity record to obtain a comparison result. If the comparison result is a preset result, the album-related data to be recommended is determined based on the compared entity records. Therefore, an embodiment of the present application provides a method for determining album-related data. Figure 3 As shown, the specific steps include:

[0103] Step 301: Create a correspondence between entity ID, entity name and entity type according to the album database to obtain at least one entity record.

[0104] The album database includes album data of multiple albums, and the album data includes multiple entity names, entity IDs, and entity types. Entities are basic objects for data recommendation, such as albums, actors, and roles. Entity IDs are unique numbers used to indicate entities, and entity types indicate the categories to which the entity belongs, such as albums, actors, and roles. For example, an entity record is <Entity Name: Zhang San, Entity Type: Actor, Entity ID: AGWE3455>, and an entity record is <Entity Name: XX Record, Entity Type: Album, Entity ID: SDEE3647>.

[0105] In the step, in the album database, the entity name, entity ID and entity type are obtained, the corresponding relationship among the entity ID, entity name and entity type is obtained, and at least one entity record is created according to the corresponding relationship.

[0106] Step 302: compare the word segmentation result with the entity name in each entity record to obtain a comparison result.

[0107] In this step, after obtaining the required entity records, these entity records are stored. When these entity records need to be used, the entity names in these entity records are obtained, and the segmentation results are compared with the entity names to obtain comparison results.

[0108] Furthermore, after obtaining the entity records, these entity records can also be classified and stored according to the entity type. For example, entity records with entity type album are stored together, entity records with entity type role are stored together, and entity records with entity type actor are stored together. In practice, the number of recommendations corresponding to each entity type is counted, and the entity record with the highest number of recommendations is first searched in the entity record where the entity type with the highest number of recommendations is located, then the entity record with the second highest number of recommendations is searched, and finally the entity record with the least number of recommendations is searched. For example, assuming that albums have the highest number of recommendations, followed by roles, and actors have the least number of recommendations, in this case, first search in the entity record with entity type album, then search in the entity record with entity type role, and finally search in the entity record with entity type actor.

[0109] Furthermore, in practice, the album with the highest popularity often has the highest number of recommendations for its related data. Therefore, the popularity of each album can also be obtained, and the popularity of each album can be used as the popularity of the entity record, so that the search order of each entity record can be determined according to the popularity.

[0110] Step 303: When the comparison result is a preset result, the album-related data to be recommended is determined according to the compared entity records.

[0111] The preset result is a comparison between a word segmentation result and an entity name in an entity record.

[0112] In this step, when the comparison result is a preset result, the entity record in the comparison is obtained, and the entity type and entity name are obtained in the entity record, and the album-related data to be recommended is searched according to the entity type and entity name.

[0113] Further, when the entity type is an album, the album-related information may be an album and a corresponding link, or other information, which is not limited here. When the entity type is a role or an actor, the album-related information may be a series of albums related to the role or actor, or other information, which is not limited here.

[0114] For example, when the hit entity record <Entity Name: XX Record, Entity Type: Album, Entity ID: SDEE3647> is found, the corresponding XX Record album and the corresponding link are found according to the entity type and entity ID, and sent to the client to recommend it to the user. When the hit entity record is <Entity Name: Zhang San, Entity Type: Actor, Entity ID: AGWE3455>, a series of albums and corresponding links starred by actor Zhang San are found according to the entity type and entity ID, and sent to the client to recommend it to the user.

[0115] In the embodiment of the present application, the entity name in some entity records may also be a noise word. Therefore, the embodiment of the present application also needs to detect whether the entity name in the entity record is a noise word. When the entity name in the entity record is a noise word, the entity record is deleted. Therefore, the embodiment of the present application also provides a method for identifying noise words. Figure 4 As shown, the specific steps include:

[0116] Step 401: Detect whether the entity name in the entity record is a noise word.

[0117] Among them, interference words are words that interfere with the entity name, such as words such as doctor, teacher, etc. Interference words are set by technicians based on experience.

[0118] In this step, the technician will pre-set the interference word library and store it in the setting device. When this step needs to be performed, the interference word library can be obtained, and the words in the interference word library can be compared with the entity name to detect whether the entity name in the entity record is a interference word.

[0119] Step 402: When the entity name in the entity record is a noise word, the entity record is deleted.

[0120] In this step, when the entity name in the entity record is a noise word, the entity record is deleted.

[0121] In the embodiments of the present application, in actual applications, many entity names have aliases. In order to optimize the recognition process and achieve more accurate entity recognition, the aliases corresponding to each entity name are fully acquired, and a close relationship between the two is established. In this way, when performing recognition work, these aliases can be used to quickly and accurately identify the corresponding entity name, greatly improving the flexibility and comprehensiveness of recognition. Therefore, the present application also provides an alias generation method, which is as follows: Figure 5 As shown, the specific steps include:

[0122] Step 501, collecting album reviews related to the album.

[0123] In this step, since some entity names are very long, their corresponding aliases are often used when users comment. In other words, there will be aliases of some entity names in album comments, so album comments related to the album can be collected to determine the aliases of the entity names.

[0124] Step 502, obtaining a reference vocabulary set according to the album reviews.

[0125] In this step, the album reviews are segmented using a preset word segmentation strategy to obtain multiple reference words, thereby forming a reference word set.

[0126] It should be noted that some of the above reference words are not aliases. Therefore, it is necessary to screen these reference words and form a reference word set based on the screened reference words.

[0127] Step 503, for each entity record, based on the entity name in the entity record, check whether there is an alias corresponding to the entity name in the reference vocabulary set. If there is an alias corresponding to the entity name, associate the entity name with the alias to generate a new entity record.

[0128] In this step, for each entity record, the similarity between the entity name in the entity record and the reference vocabulary in the reference vocabulary set can be calculated. When the similarity is greater than a preset threshold, the reference vocabulary is determined to be an alias corresponding to the entity name, and the entity name is associated with the alias to generate a new entity record.

[0129] Furthermore, in order to achieve accurate recognition and effectively reduce the amount of calculation, the following operations can also be performed for the album reviews and entity records of the same album: First, for each album review, a corresponding reference vocabulary set is generated. Then, for each entity record, its corresponding target album is determined. On this basis, based on the entity name in the entity record, whether there is an alias of the entity name in the reference vocabulary set corresponding to the target album is detected.

[0130] Additionally, the technician can check an alias in an entity record to determine whether the alias is correct or add an alias to an entity name.

[0131] In an embodiment of the present application, in actual use, since the user may make an input error, the homophone of some entity names may be entered, causing the system to be unable to recognize the corresponding entity name. In order to achieve accurate recognition, the embodiment of the present application adopts a method of generating homophones of entity names and associating these homophones with the corresponding entity names, so that the corresponding entity name can be identified by the homophones. Therefore, an embodiment of the present application provides a method for generating homophone names, the method steps of which are: for each entity record, according to the entity name in the entity record, a homophone name corresponding to each entity name is generated, the homophone name is associated with the entity name, and a new entity record is generated.

[0132] In this step, for each entity record, a homophone generation method is used according to the entity name in the entity record to generate a homophone name corresponding to each entity name, and the homophone name is associated with the entity name to generate a new entity record.

[0133] Among them, the homophone generation method can be a method based on phonetic rules, such as pinyin replacement method, phoneme analysis and replacement method, and can also be a method generated by language tools and resources, or other methods, which are not limited here.

[0134] In the embodiment of the present application, in order to enable the preset word segmentation strategy to accurately segment the text data, the preset word segmentation strategy can also be updated according to the entity name in the entity record, so that the updated preset word segmentation strategy can be used to accurately segment the text data. Therefore, the embodiment of the present application provides a preset word segmentation strategy update method, the method is as follows Figure 6 As shown, the specific steps include:

[0135] Step 601, obtain the entity name in the entity record to obtain an entity name set.

[0136] In this step, the entity names in all entity records are obtained, and these entity names are combined to obtain an entity name set.

[0137] Step 602: Update the preset word segmentation strategy according to the entity name set.

[0138] In this step, since the preset word segmentation strategy can be a rule-based word segmentation method, a deep learning-based word segmentation method, and other methods, the update strategy is different for different methods. For example, when the preset word segmentation strategy is a rule-based word segmentation method, new rules need to be written based on the entity names in the entity name set to update the existing rules. When the preset word segmentation strategy is a deep learning-based word segmentation method, the deep learning training set can be updated according to the entity names in the entity name set, and retrained based on the updated training set to obtain a new word segmentation method.

[0139] like Figure 7 As shown, the embodiment of the present application provides an album recommendation device, which corresponds to the method embodiment and specifically includes:

[0140] The receiving unit 701 is used to receive the chat data input by the user in the chat interface;

[0141] A determination unit 702, configured to determine at least one word segmentation result according to the chat data;

[0142] A search unit 703 is used to search for album-related data to be recommended in an album database according to the word segmentation result;

[0143] The sending unit 704 is used to send the album-related data to the client, so that the client displays the album-related data on the chat interface.

[0144] Optionally, the determining unit 702 is used to:

[0145] Detecting whether the chat data is voice data;

[0146] In the case where the chat data is voice data, converting the voice data into text data, and segmenting the text data using a preset word segmentation strategy to obtain at least one word segmentation result;

[0147] In the case where the chat data is text data, the preset word segmentation strategy is used to segment the text data to obtain at least one word segmentation result.

[0148] Optionally, the device further includes a creating unit 705, wherein the creating unit 705 is configured to:

[0149] According to the album database, a correspondence between entity ID, entity name and entity type is created to obtain at least one entity record;

[0150] The searching unit 703 is used for:

[0151] Compare the word segmentation result with the entity name in each entity record to obtain a comparison result;

[0152] When the comparison result is a preset result, the album-related data to be recommended is determined based on the compared entity records.

[0153] Optionally, the device further includes a detection unit 706, wherein the detection unit 706 is configured to:

[0154] Detecting whether an entity name in the entity record is a noise word;

[0155] When the entity name in the entity record is a noise word, the entity record is deleted.

[0156] Optionally, the apparatus further includes a first associating unit 707, wherein the first associating unit 707 is configured to:

[0157] Collect album reviews related to the album;

[0158] According to the album review, a reference vocabulary set is obtained;

[0159] For each entity record, based on the entity name in the entity record, it is detected in the reference vocabulary set whether there is an alias corresponding to the entity name. If there is an alias corresponding to the entity name, the entity name is associated with the alias to generate a new entity record.

[0160] Optionally, the apparatus further includes a second associating unit 708, wherein the second associating unit 808 is configured to:

[0161] For each entity record, a homophone name corresponding to each entity name is generated according to the entity name in the entity record, and the homophone name is associated with the entity name to generate a new entity record.

[0162] Optionally, the device further includes an updating unit 709, wherein the updating unit 709 is configured to:

[0163] Get the entity name in the entity record to get the entity name set;

[0164] The word segmenter is updated according to the entity name set.

[0165] like Figure 8 As shown, the embodiment of the present application provides an album recommendation device, including a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802, and the memory 803 communicate with each other through the communication bus 804.

[0166] Memory 803, used for storing computer programs;

[0167] In one embodiment of the present application, the processor 801 is used to execute the program stored in the memory 803 to implement the album recommendation method provided by any of the above method embodiments, including:

[0168] Receive chat data entered by the user in the chat interface;

[0169] Determine at least one word segmentation result according to the chat data;

[0170] According to the word segmentation result, searching the album-related data to be recommended in the album database;

[0171] The album-related data is sent to the client, so that the client displays the album-related data on the chat interface.

[0172] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the album recommendation method provided in any of the aforementioned method embodiments are implemented.

[0173] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0174] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0175] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0176] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An album recommendation method, characterized in that: The method comprises: Receive chat data entered by the user in the chat interface; Determine at least one word segmentation result according to the chat data; According to the word segmentation result, searching the album-related data to be recommended in the album database; The album-related data is sent to the client, so that the client displays the album-related data on the chat interface.

2. The method according to claim 1, characterized in that: Determining at least one word segmentation result according to the chat data includes: Detecting whether the chat data is voice data; In the case where the chat data is voice data, converting the voice data into text data, and segmenting the text data using a preset word segmentation strategy to obtain at least one word segmentation result; In the case where the chat data is text data, the preset word segmentation strategy is used to segment the text data to obtain at least one word segmentation result.

3. The method according to claim 1, characterized in that: The method further comprises: According to the album database, a correspondence between entity ID, entity name and entity type is created to obtain at least one entity record; The step of searching the album database for the album-related data to be recommended according to the word segmentation result includes: Compare the word segmentation result with the entity name in each entity record to obtain a comparison result; When the comparison result is a preset result, the album-related data to be recommended is determined based on the compared entity records.

4. The method according to claim 3, characterized in that: The method further comprises: Detecting whether an entity name in the entity record is a noise word; When the entity name in the entity record is a noise word, the entity record is deleted.

5. The method according to claim 4, characterized in that: The method further comprises: Collect album reviews related to the album; According to the album review, a reference vocabulary set is obtained; For each entity record, based on the entity name in the entity record, it is detected in the reference vocabulary set whether there is an alias corresponding to the entity name. If there is an alias corresponding to the entity name, the entity name is associated with the alias to generate a new entity record.

6. The method according to claim 4, characterized in that: The method further comprises: For each entity record, a homophone name corresponding to each entity name is generated according to the entity name in the entity record, and the homophone name is associated with the entity name to generate a new entity record.

7. The method according to claim 4, characterized in that: The method further comprises: Get the entity name in the entity record to get the entity name set; The word segmenter is updated according to the entity name set.

8. An album recommendation device, characterized in that: The device comprises: A receiving unit, used to receive chat data input by the user in the chat interface; A determination unit, configured to determine at least one word segmentation result according to the chat data; A search unit, used for searching the album-related data to be recommended in the album database according to the word segmentation result; The sending unit is used to send the album-related data to the client, so that the client displays the album-related data on the chat interface.

9. An album recommendation device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: Receive chat data entered by the user in the chat interface; Determine at least one word segmentation result according to the chat data; According to the word segmentation result, searching the album-related data to be recommended in the album database; The album-related data is sent to the client, so that the client displays the album-related data on the chat interface.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the album recommendation method according to any one of claims 1 to 7 is implemented.

Images