CN118035375A

CN118035375A - Object information acquisition method, device, computer equipment and storage medium

Info

Publication number: CN118035375A
Application number: CN202211367322.0A
Authority: CN
Inventors: 周成
Original assignee: Beijing Xiaomi Mobile Software Co Ltd; Beijing Xiaomi Pinecone Electronic Co Ltd
Current assignee: Beijing Xiaomi Mobile Software Co Ltd; Beijing Xiaomi Pinecone Electronic Co Ltd
Priority date: 2022-11-02
Filing date: 2022-11-02
Publication date: 2024-05-14

Abstract

The present disclosure proposes an object information acquisition method, apparatus, computer device, and storage medium, the method comprising: and acquiring description texts related to the objects, determining at least one target attribute value of the objects according to the description texts, wherein the description granularities corresponding to different target attribute values are different, the target attribute values describe the attribute conditions of the objects based on the corresponding description granularities, and acquiring object information according to the at least one target attribute value. By implementing the method, decoupling of the object information acquisition process can be realized based on the target attribute values with different description granularities, so that the processing difficulty of the description text is effectively reduced, and the acquisition efficiency and accuracy of the object information are improved.

Description

Object information acquisition method, device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of data processing technologies, and in particular, to a method, an apparatus, a computer device, and a storage medium for acquiring object information.

Background

With the rapid development of the internet and electronic commerce, description texts of various objects on the network are grown in mass every day, but the description texts are trivial and complex, are not classified and arranged, and are difficult to uniformly use. Thus, the user needs to extract descriptive text of different channels and different pages, and associate the descriptive text with fixed object information (such as object names) so as to analyze all descriptive text of a certain object.

In the related art, when extracting object information (object name), it is generally a rule based on a regular expression, or a neural network with an attention mechanism.

In this way, when extraction is performed based on the rule of the regular expression, the extraction process is complicated, resulting in lower efficiency, and when extraction is performed based on the neural network with the attention mechanism, the accuracy of the obtained object information cannot be ensured.

Disclosure of Invention

The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.

Therefore, an object of the present disclosure is to provide an object information obtaining method, an apparatus, a computer device, and a storage medium, which can implement decoupling of an object information obtaining process based on target attribute values with different description granularities, thereby effectively reducing processing difficulty of description text and improving obtaining efficiency and accuracy of object information.

The object information acquisition method provided by the embodiment of the first aspect of the present disclosure includes: acquiring description text related to an object; determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, and the target attribute value describes the attribute condition of the object based on the corresponding description granularities; and obtaining object information according to the at least one target attribute value.

According to the object information acquisition method provided by the embodiment of the first aspect of the present disclosure, through acquiring the description text related to the object, determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, the target attribute values describe the attribute condition of the object based on the corresponding description granularities, and acquiring the object information according to the at least one target attribute value, decoupling of the object information acquisition process can be realized based on the target attribute values with different description granularities, so that the processing difficulty of the description text is effectively reduced, and the acquisition efficiency and accuracy of the object information are improved.

An object information obtaining apparatus provided in an embodiment of a second aspect of the present disclosure includes: the first acquisition module is used for acquiring descriptive text related to the object; the determining module is used for determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, and the target attribute value describes the attribute condition of the object based on the corresponding description granularities; and a second acquisition module, configured to acquire object information according to the at least one target attribute value.

According to the object information acquisition device provided by the embodiment of the second aspect of the present disclosure, through acquiring the description text related to the object, at least one target attribute value of the object is determined according to the description text, wherein the description granularities corresponding to different target attribute values are different, the target attribute values describe the attribute condition of the object based on the corresponding description granularities, and according to the at least one target attribute value, the object information is acquired, and decoupling of the object information acquisition process can be realized based on the target attribute values with different description granularities, so that the processing difficulty of the description text is effectively reduced, and the acquisition efficiency and accuracy of the object information are improved.

Embodiments of the third aspect of the present disclosure provide a computer device, including: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the object information acquisition method according to the embodiment of the first aspect of the present disclosure when executing the program.

An embodiment of a fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements an object information acquisition method as proposed by an embodiment of the first aspect of the present disclosure.

An embodiment of a fifth aspect of the present disclosure proposes a computer program product which, when executed by a processor, performs an object information obtaining method as proposed by an embodiment of the first aspect of the present disclosure.

Additional aspects and advantages of the disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

Fig. 1 is a flowchart of an object information obtaining method according to an embodiment of the present disclosure;

fig. 2 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure;

fig. 3 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure;

fig. 4 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure;

FIG. 5 is a schematic diagram of an object information obtaining process according to an embodiment of the disclosure;

fig. 6 is a schematic diagram of a mobile phone name obtaining process according to an embodiment of the disclosure;

Fig. 7 is a schematic structural diagram of an object information acquiring apparatus according to an embodiment of the present disclosure;

fig. 8 is a schematic structural view of an object information acquiring apparatus according to another embodiment of the present disclosure;

fig. 9 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present disclosure and are not to be construed as limiting the present disclosure. On the contrary, the embodiments of the disclosure include all alternatives, modifications, and equivalents as may be included within the spirit and scope of the appended claims.

Fig. 1 is a flowchart of an object information obtaining method according to an embodiment of the present disclosure.

It should be noted that, the execution body of the object information acquiring method in this embodiment is an object information acquiring apparatus, and the apparatus may be implemented in a software and/or hardware manner, and the apparatus may be configured in a computer device, where the computer device may include, but is not limited to, a terminal, a server, and the like, and the terminal may be, for example, a mobile phone, a palm computer, and the like.

As shown in fig. 1, the object information acquisition method includes:

S101: descriptive text associated with the object is obtained.

In the embodiment of the disclosure, the object may refer to a commodity, or may refer to any other object whose object information is to be determined, such as weather information of different areas, traffic states, and the like, which is not limited.

The description text refers to text that can describe information related to the object, for example, but not limited to, internet articles, news reports, internet comments, and the like.

In the embodiment of the disclosure, when the description text related to the object is acquired, reliable reference data can be provided for acquiring the object information.

In some embodiments, when acquiring the descriptive text related to the object, a communication link between the execution body and the big data server of the embodiments of the present disclosure may be established in advance, and then the descriptive text related to the object is acquired from the big data server based on the user instruction information.

In other embodiments, when the description text related to the object is acquired, the description text related to the object can also be acquired from a data source by adopting a third-party data collection device.

Of course, any other possible method may be used to obtain the descriptive text related to the object, which is not limited.

S102: and determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, and the target attribute value describes the attribute condition of the object based on the corresponding description granularities.

Wherein the target attribute value refers to an attribute value that can be used to determine object information among a plurality of attribute values describing an object indicated by the text.

The granularity can be used for indicating the thickness degree of data statistics, and the higher the thinning degree is, the smaller the granularity level is, and the lower the thinning degree is, the larger the granularity level is. And description granularity refers to granularity of the object attribute case described by the target attribute value.

For example, the mobile phone may have target attribute information of a brand, a model, a color, etc., and a master-slave relationship exists among the brand, the model, the color, etc., so that the description granularity of the target attribute information of the brand, the model, the color, etc. for the mobile phone is different, where the brand is the largest description granularity.

In the embodiment of the disclosure, when determining at least one target attribute value of the object according to the description text, the description text may be input into a pre-trained machine learning model, and the attribute value output by the machine learning model is used as the target attribute value, or a third party determining device may be used to process the description text to obtain the target attribute value, which is not limited.

It will be appreciated that the description text may include a plurality of attribute values of the object, and that invalid attribute values may exist in the plurality of attribute values, and when determining at least one target attribute value of the object according to the description text, screening of information indicated by the description text may be implemented, so as to provide reliable reference data for subsequently acquiring object information.

S103: and acquiring object information according to at least one target attribute value.

Wherein the object information refers to related information of the object determined based on at least one target attribute value. For example, it may be an object name.

In the embodiment of the disclosure, when the object information is obtained according to the at least one target attribute value, the joint information of the at least one target attribute value may be taken as the object information, for example, when the object is a mobile phone and the object information is an object name, the brand, model, storage information, color, etc. of the mobile phone may be obtained as the target attribute value, and the brand, model, storage information, color, etc. of the mobile phone may be combined to be taken as the mobile phone name.

In this embodiment, by acquiring a description text related to an object, determining at least one target attribute value of the object according to the description text, where description granularities corresponding to different target attribute values are different, the target attribute value describes an attribute condition of the object based on corresponding description granularities, and acquiring object information according to the at least one target attribute value, decoupling of an object information acquisition process can be implemented based on the target attribute values with different description granularities, so that processing difficulty of the description text is effectively reduced, and acquisition efficiency and accuracy of the object information are improved.

Fig. 2 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure.

As shown in fig. 2, the object information acquisition method includes:

S201: descriptive text associated with the object is obtained.

The description of S201 may be specifically referred to the above embodiments, and will not be repeated here.

S202: a first target attribute of the object is determined, and at least one second target attribute associated with the first target attribute.

The first target attribute and the second target attribute refer to attributes with association relations of the objects.

In the embodiment of the disclosure, when determining the first target attribute of the object and at least one second target attribute associated with the first target attribute, a priority value corresponding to each target attribute may be determined, and the first target attribute and the second target attribute are determined from the plurality of target attributes according to the obtained priority values, for example, the range of the priority values is 0 to 1, when the object is a mobile phone, the priority corresponding to the mobile phone brand is 1, the priority corresponding to the mobile phone color is 0.1, the mobile phone brand is the first target attribute, and the mobile phone color is the second target attribute.

Or in some embodiments, the first target attribute of the object and the at least one second target attribute associated with the first target attribute may be determined based on a method of manifold combination, for example, a tree diagram may be constructed according to an association relationship between a plurality of attributes of the object, and then the first target attribute of the object and the at least one second target attribute associated with the first target attribute may be determined according to the obtained tree diagram.

Of course, any other possible method may be used to determine the first target attribute of the object, and at least one second target attribute associated with the first target attribute, which is not limited.

Optionally, in some embodiments, when determining the first target attribute of the object and at least one second target attribute associated with the first target attribute, acquiring an attribute data structure corresponding to the object, where the attribute data structure includes: the method comprises the steps that at least one father node attribute and at least one son node attribute associated with the father node attribute are different, the level of different father node attributes is different, the highest level father node attribute is taken as a first target attribute of an object, and at least one son node attribute associated with the highest level father node attribute is taken as at least one second target attribute, so that the first target attribute of the object and at least one second target attribute associated with the first target attribute can be rapidly and accurately determined based on an attribute data structure, and the reliability of the obtained first target attribute and second target attribute is effectively improved.

Wherein the attribute data structure may be used to indicate structural relationships between different attributes.

The parent node attribute refers to an attribute located at a parent node position in an attribute data structure. The child node attribute refers to an attribute of a child node having an association relationship with the parent node in the attribute data structure.

It can be appreciated that the object may have a plurality of target attributes, and there may be an association relationship between different target attributes, where the association relationship may affect the range of values of the target attributes, so when determining the first target attribute of the object and at least one second target attribute associated with the first target attribute, reliability of the target attribute value obtained later may be effectively improved.

S203: a value corresponding to the first target attribute is determined from the descriptive text as a first target attribute value.

After the first target attribute of the object is determined, the value corresponding to the first target attribute can be determined from the description text as the first target attribute value, so that accurate screening of the first target attribute value in the description text can be realized.

Optionally, in some embodiments, when determining a value corresponding to the first target attribute from the description text as the first target attribute value, the first attribute extraction model may be acquired, the description text is input into the first attribute extraction model, the value corresponding to the first target attribute output by the first attribute extraction model is obtained, and the first target attribute value is determined according to the value corresponding to the first target attribute, where the first attribute extraction model has learned a mapping relationship between the description text and the value corresponding to the first target attribute, thereby accurately and quickly determining the first target attribute value from the description text based on the first attribute extraction model, so as to effectively improve the intelligent degree of the object information acquiring process.

The attribute extraction model refers to an artificial intelligent model used for extracting target attribute values in descriptive text, and can be a named entity recognition model, for example. And the first attribute extraction model refers to an attribute extraction model used to extract a first target attribute value from the descriptive text.

S204: and determining a value corresponding to the second target attribute from the description text as a second target attribute value until a target attribute value corresponding to the minimum description granularity in the plurality of target attribute values is acquired, wherein the description granularity of the second target attribute value is smaller than that of the first target attribute value.

The minimum description granularity refers to the description granularity corresponding to the minimum value of the granularity in the plurality of description granularities. For example, a cell phone may include a number of target attributes such as make, model, run memory, storage memory, and color, where color may correspond to a minimum description granularity.

After the value corresponding to the first target attribute is determined from the description text as the first target attribute value, the value corresponding to the second target attribute may be determined from the description text as the second target attribute value until the target attribute value corresponding to the minimum description granularity of the plurality of target attribute values is obtained, so that the indication effect of the at least one target attribute value may be effectively improved based on the second target attribute value.

Alternatively, in some embodiments, when determining a value corresponding to the second target attribute from the description text as the second target attribute value, a second attribute extraction model corresponding to each second target attribute may be determined, the description text is input into the second attribute extraction model, a value corresponding to the second target attribute output by the second attribute extraction model is obtained, and the second target attribute value is determined according to the value corresponding to the second target attribute, where the second attribute extraction model has learned a mapping relationship between the description text and the value corresponding to the second target attribute, thereby effectively improving the obtaining efficiency of the second target attribute value based on the second attribute extraction model.

The second attribute extraction model is an attribute extraction model used for extracting a second target attribute.

It can be understood that there may be a difference in attribute value characteristics of different target attributes, and in the embodiment of the present disclosure, when an attribute value extraction model is obtained for a first target attribute and a second target attribute, the suitability between the obtained attribute value extraction model and the target attribute may be effectively improved, and the accuracy of attribute extraction may be improved.

That is, in the embodiment of the present disclosure, the number of target attribute values may be plural, after the description text related to the object is acquired, a first target attribute of the object and at least one second target attribute associated with the first target attribute may be determined, a value corresponding to the first target attribute is determined from the description text as the first target attribute value, a value corresponding to the second target attribute is determined from the description text as the second target attribute value, until a target attribute value corresponding to a minimum description granularity among the plural target attribute values is acquired, where the description granularity of the second target attribute value is smaller than the description granularity of the first target attribute value, thereby, the obtained at least one target attribute value may be accurately indicated for attribute information of the object based on different description granularities, so as to ensure reliability of the object information obtained based on the at least one target attribute value.

S205: and acquiring object information according to at least one target attribute value.

The description of S205 may be specifically referred to the above embodiments, and will not be repeated here.

In this embodiment, by determining a first target attribute of an object and at least one second target attribute associated with the first target attribute, determining a value corresponding to the first target attribute from a description text as a first target attribute value, determining a value corresponding to the second target attribute from the description text as a second target attribute value, until a target attribute value corresponding to a minimum description granularity among a plurality of target attribute values is obtained, where the description granularity of the second target attribute value is smaller than the description granularity of the first target attribute value, thereby enabling the obtained at least one target attribute value to accurately indicate attribute information of the object based on different description granularities, and ensuring reliability of object information obtained based on the at least one target attribute value. Obtaining an attribute data structure corresponding to the object, wherein the attribute data structure comprises: the method comprises the steps that at least one father node attribute and at least one son node attribute associated with the father node attribute are different, the level of different father node attributes is different, the highest level father node attribute is taken as a first target attribute of an object, and at least one son node attribute associated with the highest level father node attribute is taken as at least one second target attribute, so that the first target attribute of the object and at least one second target attribute associated with the first target attribute can be rapidly and accurately determined based on an attribute data structure, and the reliability of the obtained first target attribute and second target attribute is effectively improved. The first attribute extraction model is acquired, the description text is input into the first attribute extraction model, the value corresponding to the first target attribute output by the first attribute extraction model is acquired, and the first target attribute value is determined according to the value corresponding to the first target attribute, wherein the first attribute extraction model learns the mapping relation between the description text and the value corresponding to the first target attribute, so that the first target attribute value can be accurately and quickly determined from the description text based on the first attribute extraction model, and the intelligent degree of the object information acquisition process can be effectively improved. And respectively determining a second attribute extraction model corresponding to each second target attribute, inputting the description text into the second attribute extraction model, obtaining a value corresponding to the second target attribute output by the second attribute extraction model, and determining a second target attribute value according to the value corresponding to the second target attribute, wherein the second attribute extraction model has learned the mapping relation between the description text and the value corresponding to the second target attribute, thereby effectively improving the acquisition efficiency of the second target attribute value based on the second attribute extraction model.

Fig. 3 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure.

As shown in fig. 3, the object information acquisition method includes:

s301: descriptive text associated with the object is obtained.

S302: a first target attribute of the object is determined, and at least one second target attribute associated with the first target attribute.

S303: and acquiring a first attribute extraction model corresponding to the first target attribute.

S304: and inputting the description text into the first attribute extraction model, and obtaining a value corresponding to the first target attribute output by the first attribute extraction model.

The descriptions of S301 to S304 may be specifically referred to the above embodiments, and are not repeated herein.

S305: a first range of values corresponding to the first target attribute is determined.

The first value range refers to a value range of an attribute value corresponding to the first target attribute.

It will be appreciated that there may be a plurality of invalid attribute values in the descriptive text, which may interfere with the process of obtaining the first target attribute value, and when determining the first value range corresponding to the first target attribute, a reliable screening basis may be provided for determining the first target attribute value.

S306: and determining a first target attribute value according to the value corresponding to the first target attribute and the first value range.

In the embodiment of the disclosure, when determining the first target attribute value according to the value and the first value range corresponding to the first target attribute, the inclusion relationship between the value and the first value range corresponding to the first target attribute may be determined, and the first target attribute value may be determined according to the obtained inclusion relationship, or the first target attribute value may be determined according to the value and the first value range corresponding to the first target attribute by adopting a digital combination method, which is not limited.

Optionally, in some embodiments, the number of values corresponding to the first target attribute is a plurality, when determining the first target attribute value according to the value corresponding to the first target attribute and the first value range, a first matching result between the value corresponding to each first target attribute and the first value range may be determined, if the first matching result meets the first matching condition, the value corresponding to the first target attribute to which the first matching result belongs is taken as the first target attribute value, and therefore a reliable reference basis may be provided for determining the first target attribute value based on the first matching result and the first matching condition.

The first matching result refers to a matching result between a value corresponding to each first target attribute and a first value range, and may be used to indicate whether the value corresponding to the first target attribute belongs to the first value range.

The first matching condition refers to a condition configured for the first matching result in advance, and may be used to determine whether a value corresponding to a first target attribute to which the first matching result belongs may be used as the first target attribute value.

That is, in the embodiment of the present disclosure, after the descriptive text is input into the first attribute extraction model and the value corresponding to the first target attribute output by the first attribute extraction model is obtained, the first value range corresponding to the first target attribute may be determined, and the first target attribute value is determined according to the value corresponding to the first target attribute and the first value range, thereby providing reliable reference data for the determination process of the first target attribute value based on the first value range, so as to effectively improve the reliability of the obtained first target attribute value.

S307: and determining a value corresponding to the second target attribute from the description text as a second target attribute value until a target attribute value corresponding to the minimum description granularity in the plurality of target attribute values is acquired, wherein the description granularity of the second target attribute value is smaller than that of the first target attribute value.

S308: and acquiring object information according to at least one target attribute value.

The descriptions of S307 and S308 may be specifically referred to the above embodiments, and are not repeated here.

In this embodiment, by determining the first value range corresponding to the first target attribute, the first target attribute value is determined according to the value corresponding to the first target attribute and the first value range, so that reliable reference data can be provided for the determination process of the first target attribute value based on the first value range, so as to effectively improve the reliability of the obtained first target attribute value. By determining a first matching result between the value corresponding to each first target attribute and the first value range, if the first matching result meets a first matching condition, the value corresponding to the first target attribute to which the first matching result belongs is used as the first target attribute value, so that a reliable reference basis can be provided for determining the first target attribute value based on the first matching result and the first matching condition.

Fig. 4 is a flowchart of an object information acquiring method according to another embodiment of the present disclosure.

As shown in fig. 4, the object information acquisition method includes:

S401: descriptive text associated with the object is obtained.

S402: a first target attribute of the object is determined, and at least one second target attribute associated with the first target attribute.

S403: a value corresponding to the first target attribute is determined from the descriptive text as a first target attribute value.

S404: a second attribute extraction model corresponding to each second target attribute is determined separately.

S405: and inputting the description text into the second attribute extraction model, and obtaining a value corresponding to the second target attribute output by the second attribute extraction model.

The descriptions of S401 to S405 may be specifically referred to the above embodiments, and are not repeated herein.

S406: a second range of values corresponding to the second target attribute is determined.

The second value range refers to a value range of an attribute value corresponding to the second target attribute.

Optionally, in some embodiments, when determining the second value range corresponding to the second target attribute, the reference value range corresponding to the second target attribute may be determined, and the second value range is determined according to the first target attribute value and the reference value range, so that an association relationship between the first target attribute and the second target attribute may be effectively combined in a determining process of the second value range, thereby effectively improving applicability of the obtained second value range.

Wherein, the reference value range refers to a value range that may be used as the second value range.

It can be understood that the first target attribute and the second target attribute belong to the parent node and the child node respectively in the attribute data structure, so that the value range of the second target attribute may be affected by the first target attribute value, and when the second value range is determined according to the first target attribute value and the reference value range, the reliability of the obtained second value range can be effectively improved.

S407: and determining a second target attribute value according to the value corresponding to the second target attribute and the second value range.

Optionally, in some embodiments, the number of values corresponding to the second target attribute is a plurality, when determining the second target attribute value according to the value corresponding to the second target attribute and the second value range, a second matching result between the value corresponding to each second target attribute and the second value range may be determined, if the second matching result meets the second matching condition, the value corresponding to the second target attribute to which the second matching result belongs is taken as the second target attribute value, thereby providing reliable reference information for determining the second target attribute value based on the second matching result and the second matching condition, and ensuring accuracy of the obtained second target attribute value.

That is, in the embodiment of the disclosure, after the descriptive text is input into the second attribute extraction model and the value corresponding to the second target attribute output by the second attribute extraction model is obtained, the second value range corresponding to the second target attribute may be determined, and the second target attribute value is determined according to the value corresponding to the second target attribute and the second value range, so that attribute value filtering may be implemented based on the second value range in the determination process of the second target attribute value, so as to effectively improve accuracy of the obtained second target attribute value.

S408: and acquiring object information according to at least one target attribute value.

The description of S408 may be specifically referred to the above embodiments, and will not be repeated here.

In this embodiment, the second target attribute value is determined by determining the second value range corresponding to the second target attribute, and according to the value corresponding to the second target attribute and the second value range, thereby, attribute value filtering can be implemented based on the second value range in the determining process of the second target attribute value, so as to effectively improve the accuracy of the obtained second target attribute value. The second value range is determined according to the first target attribute value and the reference value range by determining the reference value range corresponding to the second target attribute, so that the association relationship between the first target attribute and the second target attribute can be effectively combined in the determination process of the second value range, and the applicability of the obtained second value range is effectively improved. And determining a second matching result between the value corresponding to each second target attribute and the second value range, and taking the value corresponding to the second target attribute to which the second matching result belongs as a second target attribute value if the second matching result meets a second matching condition, so that reliable reference information can be provided for determining the second target attribute value based on the second matching result and the second matching condition, and the accuracy of the obtained second target attribute value is ensured.

For example, as shown in fig. 5, fig. 5 is a schematic diagram of an object information obtaining process according to an embodiment of the present disclosure, after obtaining a description text related to an object, the following steps may be performed:

1. Dividing an object into a plurality of attributes according to a multi-way tree, wherein each layer of the tree represents one attribute, and each node of the tree represents different attribute values;

2. establishing a knowledge base for each attribute, i.e., selectable ranges of values for each attribute (e.g., the first and second ranges described above), for filtering those attribute values that are invalid;

3. using an attribute extraction Model 1 for the attribute 1, extracting a value attribute 1_n of the attribute 1;

4. filtering the extracted attribute 1_n by using a knowledge base;

5. Using an attribute extraction Model 2 for attribute 2, extracting a value attribute 2_n of attribute 2;

6. Filtering the extracted attributes 2_n by using a knowledge base;

7.......

8. using an attribute extraction Model i for the attribute i to extract a value attribute i_1 of the attribute i;

9. Filtering the extracted attribute i_1 by using a knowledge base;

10. And finally splicing the attributes together to form the object name.

Taking a mobile phone as an example, the mobile phone can be divided into 5 target attributes of brands, series, running memory, storage memory, color and the like, when a description text is a series B mobile phone with a brand B carrying an alpha chip, a purple body with a gold hand feeling is provided, a 6.28 inch large screen is provided, a 102Hz high-brush can be supported, a 5000-kilopixel camera is configured, 67W fast charging is supported, 8GB+128GB large memory is supported, the name of the mobile phone can be determined by using the object information acquisition method provided by the embodiment of the present disclosure, as shown in fig. 6, fig. 6 is a schematic diagram of a mobile phone name determination flow provided by the embodiment of the present disclosure, and the execution steps can be as follows:

1. Inputting a sentence: a model B mobile phone with an alpha chip is carried by a brand B, has a purple body with gold hand feeling, has a 6.28-inch large screen, can support 102Hz high-speed brushing, is provided with a camera with 5000 ten thousand pixels, and supports 67W fast charging, and 8GB+128GB large memory. Handset categories can be divided into 5 attributes: brand, model, storage memory, running memory, color, each attribute having an attribute value;

2. A knowledge base is built for the mobile phone categories, and the range of the mobile phone brands is as follows: brand a, brand B, brand C, etc., inputting the model of each brand, running memory, storage memory, color of each model;

3. extracting brands by using an attribute extraction Model model_brand corresponding to the brand attributes, filtering invalid brands by using a knowledge base, and extracting a brand 'brand B';

4. Extracting a Model by using an attribute extraction Model model_series corresponding to the Model attribute, filtering an invalid Model by using a knowledge base, and extracting a Model 'b';

5. Extracting the color by using an attribute extraction Model model_color corresponding to the color attribute, filtering invalid colors by using a knowledge base, and extracting the color purple;

6. extracting an operation memory by using an attribute extraction Model model_ram corresponding to the operation memory attribute, filtering an invalid operation memory by using a knowledge base, and extracting an operation memory '8G';

7. extracting a storage memory by using an attribute extraction Model model_rom corresponding to the storage memory attribute, filtering an invalid storage memory by using a knowledge base, and extracting a storage memory '128G';

8. and splicing the attribute values extracted from 3-7 together to obtain the brand B model B8G 128G purple, namely the name of the mobile phone.

Fig. 7 is a schematic structural diagram of an object information acquiring apparatus according to an embodiment of the present disclosure.

As shown in fig. 7, the object information acquiring apparatus 70 includes:

a first obtaining module 701, configured to obtain descriptive text related to an object;

The determining module 702 is configured to determine at least one target attribute value of the object according to the description text, where description granularities corresponding to different target attribute values are different, and the target attribute value describes an attribute condition of the object based on the corresponding description granularities; and

A second obtaining module 703, configured to obtain object information according to at least one target attribute value.

In some embodiments of the present disclosure, as shown in fig. 8, fig. 8 is a schematic structural diagram of an object information acquiring apparatus according to another embodiment of the present disclosure, where the number of target attribute values is a plurality; wherein the determining module 702 includes:

A first determination submodule 7021 for determining a first target attribute of the object and at least one second target attribute associated with the first target attribute;

a second determining submodule 7022, configured to determine, from the descriptive text, a value corresponding to the first target attribute as a first target attribute value;

And a third determining submodule 7023, configured to determine, from the description text, a value corresponding to the second target attribute as the second target attribute value until a target attribute value corresponding to a minimum description granularity in the plurality of target attribute values is obtained, where the description granularity of the second target attribute value is smaller than the description granularity of the first target attribute value.

In some embodiments of the present disclosure, the first determining submodule 7021 is specifically configured to:

Obtaining an attribute data structure corresponding to the object, wherein the attribute data structure comprises: at least one parent node attribute, and at least one child node attribute associated with the parent node attribute, the hierarchy of the different parent node attributes being different;

taking the highest-level father node attribute as a first target attribute of the object;

at least one child node attribute associated with the highest-level parent node attribute is taken as at least one second target attribute.

In some embodiments of the present disclosure, the second determination submodule 7022 is specifically configured to:

acquiring a first attribute extraction model corresponding to a first target attribute;

Inputting the description text into a first attribute extraction model, and obtaining a value corresponding to a first target attribute output by the first attribute extraction model;

And determining a first target attribute value according to the value corresponding to the first target attribute, wherein the first attribute extraction model has learned the mapping relation between the descriptive text and the value corresponding to the first target attribute.

In some embodiments of the present disclosure, the third determination submodule 7023 is specifically configured to:

respectively determining a second attribute extraction model corresponding to each second target attribute;

inputting the description text into a second attribute extraction model, and obtaining a value corresponding to a second target attribute output by the second attribute extraction model;

and determining a second target attribute value according to the value corresponding to the second target attribute, wherein the second attribute extraction model has learned the mapping relation between the descriptive text and the value corresponding to the second target attribute.

In some embodiments of the present disclosure, the second determining submodule 7022 is further configured to:

determining a first value range corresponding to the first target attribute;

and determining a first target attribute value according to the value corresponding to the first target attribute and the first value range.

In some embodiments of the present disclosure, the number of values corresponding to the first target attribute is a plurality;

wherein the second determining submodule 7022 is further configured to:

determining a first matching result between a value corresponding to each first target attribute and a first value range;

and if the first matching result meets the first matching condition, taking the value corresponding to the first target attribute to which the first matching result belongs as a first target attribute value.

In some embodiments of the present disclosure, the third determination submodule 7023 is further configured to:

Determining a second value range corresponding to the second target attribute;

and determining a second target attribute value according to the value corresponding to the second target attribute and the second value range.

determining a reference value range corresponding to the second target attribute;

and determining a second value range according to the first target attribute value and the reference value range.

In some embodiments of the present disclosure, the number of values corresponding to the second target attribute is a plurality;

wherein the third determining submodule 7023 is further configured to:

determining a second matching result between the value corresponding to each second target attribute and a second value range;

And if the second matching result meets the second matching condition, taking the value corresponding to the second target attribute to which the second matching result belongs as a second target attribute value.

It should be noted that the foregoing explanation of the method for obtaining object information is also applicable to the object information obtaining apparatus of the present embodiment, and will not be repeated here.

Fig. 9 illustrates a block diagram of an exemplary computer device suitable for use in implementing embodiments of the present disclosure. The computer device 12 shown in fig. 9 is merely an example and should not be construed as limiting the functionality and scope of use of the disclosed embodiments.

As shown in fig. 9, the computer device 12 is in the form of a general purpose computing device. Components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.

Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include industry Standard architecture (Industry Standard Architecture; hereinafter ISA) bus, micro channel architecture (Micro Channel Architecture; hereinafter MAC) bus, enhanced ISA bus, video electronics standards Association (Video Electronics Standards Association; hereinafter VESA) local bus, and peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECTION; hereinafter PCI) bus.

Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (Random Access Memory; hereinafter: RAM) 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 9, commonly referred to as a "hard disk drive").

Although not shown in fig. 9, a disk drive for reading from and writing to a removable nonvolatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable nonvolatile optical disk (e.g., a compact disk read only memory (Compact Disc Read Only Memory; hereinafter, "CD-ROM"), digital versatile read only optical disk (Digital Video Disc Read Only Memory; hereinafter, "DVD-ROM"), or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of the various embodiments of the disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods in the embodiments described in this disclosure.

The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a person to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Moreover, the computer device 12 may also communicate with one or more networks such as a local area network (Local Area Network; hereinafter: LAN), a wide area network (Wide Area Network; hereinafter: WAN) and/or a public network such as the Internet via the network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

The processing unit 16 executes various functional applications and data processing by running a program stored in the system memory 28, for example, implementing the object information acquisition method mentioned in the foregoing embodiment.

In order to implement the above-described embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements an object information acquisition method as proposed in the foregoing embodiments of the present disclosure.

In order to implement the above-described embodiments, the present disclosure also proposes a computer program product which, when executed by an instruction processor in the computer program product, performs the object information acquisition method as proposed in the foregoing embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

It should be noted that in the description of the present disclosure, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Furthermore, in the description of the present disclosure, unless otherwise indicated, the meaning of "a plurality" is two or more.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present disclosure in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

Furthermore, each functional unit in the embodiments of the present disclosure may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.

Claims

1. An object information acquisition method, characterized by comprising:

acquiring description text related to an object;

Determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, and the target attribute value describes the attribute condition of the object based on the corresponding description granularities; and

And acquiring object information according to the at least one target attribute value.

2. The method of claim 1, wherein the number of target attribute values is a plurality; wherein said determining at least one target attribute value for said object from said descriptive text comprises:

Determining a first target attribute of the object and at least one second target attribute associated with the first target attribute;

Determining a value corresponding to the first target attribute from the descriptive text as the first target attribute value;

And determining a value corresponding to the second target attribute from the description text as the second target attribute value until a target attribute value corresponding to the minimum description granularity in a plurality of target attribute values is acquired, wherein the description granularity of the second target attribute value is smaller than that of the first target attribute value.

3. The method of claim 2, wherein the determining the first target attribute of the object and the at least one second target attribute associated with the first target attribute comprises:

obtaining an attribute data structure corresponding to the object, wherein the attribute data structure comprises: at least one parent node attribute, and at least one child node attribute associated with the parent node attribute, the hierarchy of different parent node attributes being different;

And taking at least one child node attribute associated with the highest-level parent node attribute as the at least one second target attribute.

4. The method of claim 2, wherein the determining, from the descriptive text, a value corresponding to the first target attribute as the first target attribute value comprises:

acquiring a first attribute extraction model corresponding to the first target attribute;

Inputting the description text into the first attribute extraction model, and obtaining a value corresponding to the first target attribute output by the first attribute extraction model;

And determining the first target attribute value according to the value corresponding to the first target attribute, wherein the first attribute extraction model learns the mapping relation between the description text and the value corresponding to the first target attribute.

5. The method of claim 2, wherein the determining, from the descriptive text, a value corresponding to the second target attribute as the second target attribute value comprises:

inputting the description text into the second attribute extraction model, and obtaining a value corresponding to the second target attribute output by the second attribute extraction model;

And determining the value of the second target attribute according to the value corresponding to the second target attribute, wherein the second attribute extraction model learns the mapping relation between the descriptive text and the value corresponding to the second target attribute.

6. The method of claim 4, wherein the determining the first target attribute value from the value corresponding to the first target attribute comprises:

determining a first value range corresponding to the first target attribute;

And determining the value of the first target attribute according to the value corresponding to the first target attribute and the first value range.

7. The method of claim 6, wherein the number of values corresponding to the first target attribute is a plurality;

wherein the determining the first target attribute value according to the value corresponding to the first target attribute and the first value range includes:

determining a first matching result between the value corresponding to each first target attribute and the first value range;

and if the first matching result meets a first matching condition, taking a value corresponding to the first target attribute to which the first matching result belongs as the first target attribute value.

8. The method of claim 5, wherein said determining said second target attribute value from said value corresponding to said second target attribute comprises:

Determining a second value range corresponding to the second target attribute;

And determining the value of the second target attribute according to the value corresponding to the second target attribute and the second value range.

9. The method of claim 8, wherein the determining a second range of values corresponding to the second target attribute comprises:

and determining the second value range according to the first target attribute value and the reference value range.

10. The method of claim 8, wherein the number of values corresponding to the second target attribute is a plurality;

Wherein the determining the second target attribute value according to the value corresponding to the second target attribute and the second value range includes:

determining a second matching result between the value corresponding to each second target attribute and the second value range;

and if the second matching result meets a second matching condition, taking a value corresponding to the second target attribute to which the second matching result belongs as the second target attribute value.

11. An object information acquisition apparatus, characterized by comprising:

the first acquisition module is used for acquiring descriptive text related to the object;

The determining module is used for determining at least one target attribute value of the object according to the description text, wherein the description granularities corresponding to different target attribute values are different, and the target attribute value describes the attribute condition of the object based on the corresponding description granularities; and

And the second acquisition module is used for acquiring the object information according to the at least one target attribute value.

12. The apparatus of claim 11, wherein the number of target attribute values is a plurality; wherein, the determining module includes:

a first determination sub-module for determining a first target attribute of the object, and at least one second target attribute associated with the first target attribute;

a second determining submodule, configured to determine, from the description text, a value corresponding to the first target attribute as the first target attribute value;

And the third determining submodule is used for determining a value corresponding to the second target attribute from the description text as the second target attribute value until the target attribute value corresponding to the minimum description granularity in the target attribute values is acquired, wherein the description granularity of the second target attribute value is smaller than that of the first target attribute value.

13. The apparatus of claim 12, wherein the first determination submodule is specifically configured to:

14. The apparatus of claim 12, wherein the second determination submodule is specifically configured to:

15. The apparatus of claim 12, wherein the third determination submodule is specifically configured to:

16. The apparatus of claim 14, wherein the second determination submodule is further to:

determining a first value range corresponding to the first target attribute;

17. The apparatus of claim 16, wherein the number of values corresponding to the first target attribute is a plurality;

wherein the second determination submodule is further configured to:

18. The apparatus of claim 15, wherein the third determination submodule is further to:

Determining a second value range corresponding to the second target attribute;

19. The apparatus of claim 18, wherein the third determination submodule is further to:

20. The apparatus of claim 18, wherein the number of values corresponding to the second target attribute is a plurality;

Wherein the third determination submodule is further configured to:

21. A computer device, comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions are for causing the computer to perform the method of any one of claims 1-10.

23. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1-10.